HENGCDHENGCD INDUSTRIAL AIMODEL PRICING
Prix modèles et points clairs
Consultez au même endroit les tarifs, l’intégration au connecteur et les conditions de disponibilité. L’accès réel dépend de la clé API et de la route serveur.
01
Contenu de la page
Consultez au même endroit les tarifs, l’intégration au connecteur et les conditions de disponibilité. L’accès réel dépend de la clé API et de la route serveur.
Cette page est un aperçu traduit. La version chinoise fait foi pour les détails techniques et contractuels.
Les nombres proviennent des listes publiées pour chaque accès, sans doublon au sein d’un studio. Un modèle peut figurer dans plusieurs studios. L’accès et les fonctions dépendent des droits de la clé API, des routes serveur et des spécifications du modèle.
Completed capability declarations: 44. Each covers its stated deployment scope; model notes retain limits and pending items.
Les tarifs Token sont exprimés en points par million de Tokens. Les autres capacités utilisent leur unité affichée. Les paliers dépendent du tarif de chaque modèle. Le compte suit la consommation réelle ; le coefficient API Key concerne uniquement les points de la clé. Les services ouverts déduisent des points selon l’usage réel. La recharge en ligne et l’émission de factures restent indisponibles.
ModèleConsommation de points
Les modèles indépendants sont prioritaires. Un instantané ou alias est retenu seulement s’il constitue le seul accès disponible pour la même plateforme, génération et famille de capacités. Tous les types permet de consulter les autres versions, avec leurs propres codes, prix et états. Des données manquantes ou une relation non résolue ne signifient pas une indisponibilité. Les voix et services ne sont pas de nouveaux modèles de base. Les routes API et certifications restent inchangées.
Affichés / total: 482 / 613Claude Haiku 5.5
Vérification en attente (UTC+8)
claude-haiku-5-5Modèle indépendantAnthropic · Stable2026-10-07Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance—Valeur—
Non évaluéUsage entrée · par million de Tokens200 000 pointsLecture du cache · par million de Tokens20 000 pointsUsage écriture cache · 5m · par million de Tokens250 000 pointsUsage écriture cache · 1h · par million de Tokens400 000 pointsUsage sortie · par million de Tokens1 000 000 pointsRecherche Web · par 1 000 unités de recherche20 000 000 points
Claude Haiku 5.5-100
claude-haiku-5-5-100Modèle indépendantAnthropic · Stable2026-10-07Pas de prix fixe ; facturation selon le servicePerformance · Estimated74.7Valeur · Estimated82.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
Non évalué · Confidence 0%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Tarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Gemini Nano Banana 2.1-100
Vérification en attente (UTC+8)
gemini-nano-banana-2.1Modèle indépendantGoogle · Stable2026-10-06Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance92.5Valeur · Estimated66.5
Provisoire
Non évalué · Confidence 0%Usage entrée · par million de Tokens3 000 000 pointsUsage entrée · Image · par million de Tokens3 000 000 pointsLecture du cache · par million de Tokens300 000 pointsUsage sortie · par million de Tokens15 000 000 pointsLecture du cache · Image · par million de Tokens300 000 pointsUsage sortie · Image · par million de Tokens60 000 000 points
Qwen-Image-2.1-Pro
Vérification en attente (UTC+8)
qwen-image-2.1-proModèle indépendantQwen · Stable2026-10-02Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated66.4Valeur · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentUsage sortie · Image · par image68 494 points
Grok 4.7-100
Vérification en attente (UTC+8)
grok-4.7-100Modèle indépendantxAI · Aperçu2026-09-30Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance—Valeur—
Non évaluéUsage entrée · par million de Tokens4 000 000 pointsLecture du cache · par million de Tokens1 000 000 pointsUsage sortie · par million de Tokens12 000 000 points
GPT-6.1 Sol
Vérification en attente (UTC+8)
gpt-6.1-solModèle indépendantOpenAI · Stable2026-09-29Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated82.2Valeur · Estimated69.2
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.4 (estimated) · 5/19 observed / reasoning 85.3 (estimated) · 3/13 observed / writing 84.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-6-astra · 1 benchmarksReference: gpt-6-luna · 1 benchmarksReference: gpt-6-sol · 1 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens4 000 000 pointsLecture du cache · par million de Tokens200 000 pointsUsage écriture cache · par million de Tokens5 000 000 pointsUsage sortie · par million de Tokens20 000 000 points
Claude Sonnet 5.5
Vérification en attente (UTC+8)
claude-sonnet-5-5Modèle indépendantAnthropic · Stable2026-09-28Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated74.4Valeur · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 84.5 (estimated) · 5/19 observed / reasoning 78.8 (estimated) · 3/13 observed / writing 59.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens4 000 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage écriture cache · 5m · par million de Tokens5 000 000 pointsUsage écriture cache · 1h · par million de Tokens8 000 000 pointsUsage sortie · par million de Tokens20 000 000 pointsRecherche Web · par 1 000 unités de recherche20 000 000 points
Claude Sonnet 5.5-100
claude-sonnet-5-5-100Modèle indépendantAnthropic · Stable2026-09-28Pas de prix fixe ; facturation selon le servicePerformance · Estimated74.4Valeur · Estimated67.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 84.5 (estimated) · 0/19 observed / reasoning 78.8 (estimated) · 0/13 observed / writing 59.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-5-5 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
决策模型（预览版）
Vérification en attente (UTC+8)
decision-model-previewModèle indépendantQwen · Stable2026-09-24Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens0 points
Gemini 3.8 Live-100
Vérification en attente (UTC+8)
gemini-3.8-liveModèle indépendantGoogle · Stable2026-09-24Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated76.9Valeur · Estimated68.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.9 (estimated) · 0/19 observed / reasoning 76.8 (estimated) · 0/13 observed / writing 87.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.8-flash-high · 7 benchmarksReference: gemini-4-argon-high · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 500 000 pointsEntrée vidéo · par million de Tokens2 000 000 pointsUsage entrée · Audio · par million de Tokens6 000 000 pointsUsage sortie · par million de Tokens9 000 000 pointsUsage sortie · Audio · par million de Tokens24 000 000 pointsUsage sortie · Génération vidéo · par million de Tokens2 000 000 points
Claude Opus 5.5
Vérification en attente (UTC+8)
claude-opus-5-5Modèle indépendantAnthropic · Stable2026-09-22Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated86.9Valeur · Estimated69.6
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 91.4 (estimated) · 5/19 observed / reasoning 94.0 (estimated) · 4/13 observed / writing 75.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens8 000 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage écriture cache · 5m · par million de Tokens10 000 000 pointsUsage écriture cache · 1h · par million de Tokens16 000 000 pointsUsage sortie · par million de Tokens40 000 000 pointsRecherche Web · par 1 000 unités de recherche20 000 000 points
Claude Opus 5.5-100
claude-opus-5-5-100Modèle indépendantAnthropic · Stable2026-09-22Pas de prix fixe ; facturation selon le servicePerformance · Estimated86.9Valeur · Estimated75.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 91.4 (estimated) · 0/19 observed / reasoning 94.0 (estimated) · 0/13 observed / writing 75.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-5-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT-6 Luna
Vérification en attente (UTC+8)
gpt-6-lunaModèle indépendantOpenAI · Stable2026-09-22Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated59.4Valeur · Estimated65.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.8 (estimated) · 5/19 observed / reasoning 64.0 (estimated) · 4/13 observed / writing 50.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.6-luna by 4.3 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens200 000 pointsLecture du cache · par million de Tokens20 000 pointsUsage écriture cache · par million de Tokens250 000 pointsUsage sortie · par million de Tokens1 000 000 points
GPT-6 Sol
Vérification en attente (UTC+8)
gpt-6-solModèle indépendantOpenAI · Stable2026-09-22Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated74.3Valeur · Estimated63.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 74.6 (estimated) · 5/19 observed / reasoning 78.4 (estimated) · 4/13 observed / writing 69.9 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.6-sol by 8.8 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens4 000 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage écriture cache · par million de Tokens5 000 000 pointsUsage sortie · par million de Tokens20 000 000 points
Grok 4.7
Vérification en attente (UTC+8)
grok-4.7Modèle indépendantxAI · Stable2026-09-21Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance—Valeur—
Non évaluéUsage entrée · par million de Tokens4 000 000 pointsLecture du cache · par million de Tokens1 000 000 pointsUsage sortie · par million de Tokens12 000 000 points
Qwen-Audio-3.1-Realtime-Plus
qwen-audio-3.1-realtime-plusModèle indépendantQwen · Stable2026-09-20Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3.8-Livetranslate-Flash-Realtime
qwen3.8-livetranslate-flash-realtimeModèle indépendantQwen · Stable2026-09-18Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-MT-Uni
qwen-mt-uniModèle indépendantQwen · Stable2026-09-16Pas de prix fixe ; facturation selon le servicePerformance · Estimated49.4Valeur · Estimated49.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.5 (estimated) · 0/19 observed / reasoning 54.8 (estimated) · 0/13 observed / writing 47.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: qwen-14b-chat · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-kimi/kimi-k2.8-preview
Vérification en attente (UTC+8)
qwen-kimi-kimi-k2.8-previewModèle indépendantMoonshot AI · Stable2026-09-11Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 780 822 pointsLecture du cache · par million de Tokens465 753 pointsUsage sortie · par million de Tokens7 397 260 points
DeepSeek V4.1 Flash
Vérification en attente (UTC+8)
deepseek-flashModèle indépendantDeepSeek · Stable2026-09-10Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated78.1Valeur · Estimated77.6
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 81.2 (estimated) · 4/19 observed / reasoning 82.4 (estimated) · 4/13 observed / writing 70.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksEstimated value uses this exact model's reviewed off-peak public point rates and the shared text workload. Weekday peak rates double; public holidays use off-peak rates. It is not a measured charge.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentUsage entrée · par million de Tokens300 000 pointsLecture du cache · par million de Tokens6 000 pointsUsage sortie · par million de Tokens1 200 000 points
doubao-deepseek-v4-1-flash
Vérification en attente (UTC+8)
doubao-deepseek-v4-1-flash-260910Instantané / version fixe · Accès uniqueDeepSeek · Stable2026-09-10Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens273 973 pointsLecture du cache · par million de Tokens5 479 pointsUsage sortie · par million de Tokens1 095 890 points
qwen-DeepSeek V4.1 Flash
Vérification en attente (UTC+8)
qwen-deepseek-v4.1-flashModèle indépendantDeepSeek · Stable2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated61.4Valeur · Estimated66.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens273 973 pointsLecture du cache · par million de Tokens27 397 pointsUsage sortie · par million de Tokens1 095 890 points
qwen-vanchin/deepseek-v4.1-flash
qwen-vanchin-deepseek-v4.1-flashModèle indépendantDeepSeek · Stable2026-09-10Pas de prix fixe ; facturation selon le servicePerformance · Estimated61.4Valeur · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT Image 2.5 Flare
Vérification en attente (UTC+8)
gpt-image-2.5-flareModèle indépendantOpenAI · Stable2026-09-08Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance98.5Valeur70.3
Usage entrée · par million de Tokens10 000 000 pointsLecture du cache · par million de Tokens2 500 000 pointsUsage entrée · Image · par million de Tokens16 000 000 pointsLecture du cache · Image · par million de Tokens4 000 000 pointsUsage sortie · Image · par million de Tokens60 000 000 points
GPT Image 2.5 Sunburst
Vérification en attente (UTC+8)
gpt-image-2.5-sunburstModèle indépendantOpenAI · Stable2026-09-08Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance100.0Valeur71.4
Usage entrée · par million de Tokens10 000 000 pointsLecture du cache · par million de Tokens2 500 000 pointsUsage entrée · Image · par million de Tokens16 000 000 pointsLecture du cache · Image · par million de Tokens4 000 000 pointsUsage sortie · Image · par million de Tokens60 000 000 points
GPT-6 Astra
Vérification en attente (UTC+8)
gpt-6-astraModèle indépendantOpenAI · Stable2026-09-03Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated85.4Valeur · Estimated64.8
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 79.9 (estimated) · 5/19 observed / reasoning 92.0 (estimated) · 4/13 observed / writing 84.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens20 000 000 pointsLecture du cache · par million de Tokens2 000 000 pointsUsage écriture cache · par million de Tokens25 000 000 pointsUsage sortie · par million de Tokens100 000 000 points
Gemini 3.8 Flash-100
Vérification en attente (UTC+8)
gemini-3.8-flash-100Modèle indépendantGoogle · Stable2026-09-02Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance—Valeur—
Non évaluéUsage entrée · par million de Tokens3 000 000 pointsUsage entrée · Image · par million de Tokens3 000 000 pointsUsage entrée · Audio · par million de Tokens3 000 000 pointsEntrée vidéo · par million de Tokens3 000 000 pointsLecture du cache · par million de Tokens300 000 pointsUsage sortie · par million de Tokens15 000 000 pointsUsage écriture cache · par million de Tokens3 000 000 pointsStockage du cache explicite · par million de tokens-heures2 000 000 points
Claude Fable 5.1
Vérification en attente (UTC+8)
claude-fable-5-1Modèle indépendantAnthropic · Stable2026-09-01Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated89.2Valeur · Estimated67.4
Shared exact-model performance from claude-fable-5-1; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 90.5 (estimated) · 5/19 observed / reasoning 93.8 (estimated) · 4/13 observed / writing 83.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens20 000 000 pointsLecture du cache · par million de Tokens500 000 pointsUsage écriture cache · 5m · par million de Tokens25 000 000 pointsUsage écriture cache · 1h · par million de Tokens40 000 000 pointsUsage sortie · par million de Tokens100 000 000 pointsRecherche Web · par 1 000 unités de recherche20 000 000 points
Claude Fable 5.1-100
claude-fable-5-1-100Modèle indépendantAnthropic · Stable2026-09-01Pas de prix fixe ; facturation selon le servicePerformance · Estimated89.2Valeur—
Shared exact-model performance from claude-fable-5-1; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 90.5 (estimated) · 5/19 observed / reasoning 93.8 (estimated) · 4/13 observed / writing 83.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Doubao-Seed-2.1-Lite
Vérification en attente (UTC+8)
doubao-seed-2-1-lite-260915Instantané / version fixe · Accès uniqueDoubao · Stable2026-09 (mois officiel uniquement)Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated63.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 56.6microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens43 836 pointsUsage sortie · par million de Tokens739 726 points
doubao-seedream-5-0-flash
doubao-seedream-5-0-flash-260915Instantané / version fixe · Accès uniqueDoubao · Stable2026-09 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated65.8Valeur · Estimated61.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-5.0-lite · 50.2Reference: seedream-5.0-pro · 85.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
千问3.7-通用文本向量-flash
Vérification en attente (UTC+8)
qwen3.7-text-embedding-flashModèle indépendantAlibaba Cloud · Stable2026-09-01Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.3Valeur · Estimated73.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEntrée vectorielle · par million de Tokens34 247 points
千问3.7-通用文本重排序
Vérification en attente (UTC+8)
qwen3.7-text-rerankModèle indépendantAlibaba Cloud · Stable2026-09-01Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated72.5Valeur · Estimated80.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · OfficialUsage entrée · par million de Tokens136 987 points
Qwen3.8-Omni-Flash
qwen3.8-omni-flashModèle indépendantQwen · Stable2026-09 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated61.4Valeur · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3.8-Omni-Flash-Realtime
qwen3.8-omni-flash-realtimeModèle indépendantQwen · Stable2026-09 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-MT-Image-2.0
qwen-mt-image-2.0Modèle indépendantQwen · Stable2026-08-28Pas de prix fixe ; facturation selon le servicePerformance · Estimated73.8Valeur · Estimated66.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Cohere Parse v5
Vérification en attente (UTC+8)
cohere-parse-v5Modèle indépendantCohere · Aperçu2026-08-27Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance79.2Valeur85.4
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 18%cohere-parsebench · OfficialTraitement documentaire · par 1 000 pages3 000 000 points
Gemini Omni 1.1 Flash Preview-100
gemini-omni-1.1-flash-previewModèle indépendantGoogle · Stable2026-08-27Pas de prix fixe ; facturation selon le servicePerformance · Estimated49.9Valeur · Estimated49.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.2 (estimated) · 0/19 observed / reasoning 44.4 (estimated) · 0/13 observed / writing 59.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.5-flash-high · 7 benchmarksReference: gemini-1.5-flash-001 · 4 benchmarksReference: gemini-1.5-flash-002 · 4 benchmarksReference: gemini-1.5-flash-8b-001 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ZHIPU/GLM-5.3-Flash
Vérification en attente (UTC+8)
qwen-zhipu-glm-5.3-flashModèle indépendantZhipu AI · Stable2026-08-26Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated48.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens63 014 pointsUsage sortie · par million de Tokens767 123 points
Qwen3.8-Flash
Vérification en attente (UTC+8)
qwen3.8-flashModèle indépendantQwen · Stable2026-08-25Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated61.4Valeur · Estimated67.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens27 397 pointsUsage sortie · par million de Tokens739 726 points
qwen-Kimi-K3
Vérification en attente (UTC+8)
qwen-kimi-k3Modèle indépendantMoonshot · Stable2026-08-19Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated39.7Valeur · Estimated38.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 35.6 (estimated) · 0/19 observed / reasoning 49.2 (estimated) · 0/13 observed / writing 34.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens5 479 452 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens27 397 260 points
Qwen3.8-27B
Vérification en attente (UTC+8)
qwen3.8-27bModèle indépendantQwen · Stable2026-08-17Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated65.0Valeur · Estimated64.2
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 5/19 observed / reasoning 68.3 (estimated) · 4/13 observed / writing 62.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens821 918 pointsLecture du cache · par million de Tokens164 384 pointsUsage sortie · par million de Tokens3 287 671 points
qwen-GLM-5.3
Vérification en attente (UTC+8)
qwen-glm-5.3Modèle indépendantZhipu AI · Stable2026-08-14Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated61.1Valeur · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens7 671 233 points
qwen-ZHIPU/GLM-5.3
Vérification en attente (UTC+8)
qwen-zhipu-glm-5.3Modèle indépendantZhipu AI · Stable2026-08-14Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens7 671 233 points
DeepSeek V4 Pro
Vérification en attente (UTC+8)
deepseek-v4-proModèle indépendantDeepSeek · Stable2026-08-13Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated64.4Valeur · Estimated62.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.8 (estimated) · 0/19 observed / reasoning 74.3 (estimated) · 0/13 observed / writing 65.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: deepseek-v4-pro · 7 benchmarksReference: deepseek-v4-pro-0813 · 7 benchmarksReference: deepseek-v4-pro · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 320 000 pointsLecture du cache · par million de Tokens44 000 pointsUsage sortie · par million de Tokens3 960 000 points
GLM-5.3
Vérification en attente (UTC+8)
glm-5.3Modèle indépendantZhipu · Stable2026-08-13Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated71.7Valeur · Estimated65.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.9 (estimated) · 0/19 observed / reasoning 71.1 (estimated) · 0/13 observed / writing 70.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.3 · 7 benchmarksReference: glm-5.2 · 6 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens7 671 233 points
GLM-5.3-Flash
Vérification en attente (UTC+8)
glm-5.3-flashModèle indépendantZhipu · Stable2026-08-13Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated65.1Valeur · Estimated70.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 69.5 (estimated) · 0/19 observed / reasoning 68.7 (estimated) · 0/13 observed / writing 57.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: glm-5.3-flash · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens63 014 pointsUsage sortie · par million de Tokens767 123 points
Grok 4.6
Vérification en attente (UTC+8)
grok-4.6Modèle indépendantxAI · Aperçu2026-08-12Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated70.4Valeur · Estimated61.9
Shared exact-model performance from grok-4.6; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.3 (estimated) · 5/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 73.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens8 000 000 pointsLecture du cache · par million de Tokens2 000 000 pointsUsage sortie · par million de Tokens24 000 000 points
Grok 4.6-100
grok-4.6-100Modèle indépendantxAI · Stable2026-08-12Pas de prix fixe ; facturation selon le servicePerformance · Estimated70.4Valeur—
Shared exact-model performance from grok-4.6; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.3 (estimated) · 5/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 73.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
MAI Thinking 1
Vérification en attente (UTC+8)
mai-thinking-1Modèle indépendantMicrosoft AI · Aperçu2026-08-12Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated51.7
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 18%coding 56.8 (estimated) · 4/19 observed / reasoning 60.2 (estimated) · 5/13 observed / writing 52.8 (estimated) · 3/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens4 000 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage sortie · par million de Tokens16 000 000 points
Qwen3.8-2.4T-A95B
Vérification en attente (UTC+8)
qwen3.8-2.4t-a95bModèle indépendantQwen · Stable2026-08-12Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated65.0Valeur · Estimated58.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 0/19 observed / reasoning 68.3 (estimated) · 0/13 observed / writing 62.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-27b · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens3 287 671 pointsLecture du cache · par million de Tokens410 959 pointsUsage sortie · par million de Tokens9 863 014 points
万相3.0-视频生成
Vérification en attente (UTC+8)
wan3.0-videoModèle indépendantAlibaba Cloud · Stable2026-08-06Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated92.6Valeur · Estimated72.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan3.0 · 92.6arena · Independentarena · IndependentGénération vidéo 480P · par seconde57 535 pointsGénération vidéo 720P · par seconde115 069 pointsGénération vidéo 1080P · par seconde230 137 points
Qwen3.8-Max
Vérification en attente (UTC+8)
qwen3.8-maxModèle indépendantQwen · Stable2026-08-02Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated76.0Valeur · Estimated66.6
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 70.3 (estimated) · 5/19 observed / reasoning 82.3 (estimated) · 4/13 observed / writing 75.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens3 287 671 pointsLecture du cache · par million de Tokens410 959 pointsUsage sortie · par million de Tokens9 863 014 points
Gemini 3.5 Transcribe Live Preview-100
gemini-3.5-transcribe-live-previewModèle indépendantGoogle · Stable2026-08 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Gemini 3.5 Transcribe Preview-100
gemini-3.5-transcribe-previewModèle indépendantGoogle · Stable2026-08 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
doubao-DeepSeek V4 Flash GA (2026-07-31)
Vérification en attente (UTC+8)
doubao-deepseek-v4-flash-ga-260731Instantané / version fixe · Accès uniqueDeepSeek · Stable2026-07-31Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated58.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens821 918 pointsLecture du cache · par million de Tokens27 397 pointsUsage sortie · par million de Tokens2 465 753 points
qwen-MiniMax/MiniMax-H3
qwen-minimax-minimax-h3Modèle indépendantmini-max · Stable2026-07-31Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Audio-3.0-ASR-Flash
Vérification en attente (UTC+8)
qwen-audio-3.0-asr-flashModèle indépendantAlibaba Cloud · Stable2026-07-30Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.4Valeur · Estimated94.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · par seconde61 points
qwen-audio-3.0-asr-flash-filetrans
qwen-audio-3.0-asr-flash-filetransModèle indépendantQwen · Stable2026-07-30Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Audio-3.0-ASR-Flash-Streaming
qwen-audio-3.0-asr-flash-streamingModèle indépendantQwen · Stable2026-07-30Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT Live Transcribe
Vérification en attente (UTC+8)
gpt-live-transcribeModèle indépendantOpenAI · Stable2026-07-28Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.4Valeur · Estimated64.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · par heure2 040 000 points
GPT Transcribe
Vérification en attente (UTC+8)
gpt-transcribeModèle indépendantOpenAI · Stable2026-07-28Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.4Valeur · Estimated81.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · par heure540 000 points
qwen-PixVerse-V6-r2v-omni
qwen-pixverse-pixverse-v6-r2v-omniModèle indépendantpixverse · Stable2026-07-26Pas de prix fixe ; facturation selon le servicePerformance · Estimated61.1Valeur · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Claude Opus 5
Vérification en attente (UTC+8)
claude-opus-5Modèle indépendantAnthropic · Stable2026-07-24Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated81.9Valeur · Estimated65.2
Shared exact-model performance from claude-opus-5; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.2 (estimated) · 5/19 observed / reasoning 86.3 (estimated) · 4/13 observed / writing 74.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens10 000 000 pointsLecture du cache · par million de Tokens1 000 000 pointsUsage écriture cache · 5m · par million de Tokens12 500 000 pointsUsage écriture cache · 1h · par million de Tokens20 000 000 pointsUsage sortie · par million de Tokens50 000 000 points
Claude Opus 5-100
claude-opus-5-100Modèle indépendantAnthropic · Stable2026-07-24Pas de prix fixe ; facturation selon le servicePerformance · Estimated81.9Valeur—
Shared exact-model performance from claude-opus-5; coverage refers to public model benchmarks, not tests of every platform deployment.Version comparison review13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.2 (estimated) · 5/19 observed / reasoning 86.3 (estimated) · 4/13 observed / writing 74.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-opus-5-5-100 by 5.0 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Gemini 3.5 Flash-Lite-100
Vérification en attente (UTC+8)
gemini-3.5-flash-lite-100Modèle indépendantGoogle · Stable2026-07-21Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated52.3Valeur · Estimated55.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.1 (estimated) · 0/19 observed / reasoning 52.8 (estimated) · 0/13 observed / writing 56.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.5-flash-lite-high · 7 benchmarksReference: gemini-3.5-flash-lite · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens600 000 pointsLecture du cache · par million de Tokens60 000 pointsUsage sortie · par million de Tokens5 000 000 points
Qwen3.7-Flash
Vérification en attente (UTC+8)
qwen3.7-flashModèle indépendantQwen · Stable2026-07-21Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated61.4Valeur · Estimated73.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32 000 TokenUsage entrée · par million de Tokens54 795 pointsLecture du cache · par million de Tokens10 959 pointsUsage sortie · par million de Tokens219 178 points
Input 32 001 – 256 000 TokenUsage entrée · par million de Tokens164 384 pointsLecture du cache · par million de Tokens32 877 pointsUsage sortie · par million de Tokens657 534 points
Input 256 001+ TokenUsage entrée · par million de Tokens328 767 pointsLecture du cache · par million de Tokens65 753 pointsUsage sortie · par million de Tokens1 315 068 points
Qwen-Image-3.0
Vérification en attente (UTC+8)
qwen-image-3.0Modèle indépendantAlibaba Cloud · Stable2026-07-21Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated73.8Valeur · Estimated81.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8arena · Independentarena · IndependentImage Usage entrée 1K · par image5 480 pointsImage Usage entrée 2K · par image5 480 pointsImage Usage sortie 1K · par image49 316 pointsImage Usage sortie 2K · par image49 316 points
Kimi K3
Vérification en attente (UTC+8)
kimi-k3Modèle indépendantMoonshot · Stable2026-07-16Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated80.1Valeur · Estimated66.4
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 81.7 (estimated) · 5/19 observed / reasoning 80.2 (estimated) · 4/13 observed / writing 78.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens5 479 452 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens27 397 260 points
qwen-kimi/kimi-k3
Vérification en attente (UTC+8)
qwen-kimi-kimi-k3Modèle indépendantMoonshot AI · Stable2026-07-16Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens5 479 452 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens27 397 260 points
Qwen3.7-通用文本向量
Vérification en attente (UTC+8)
qwen3.7-text-embeddingModèle indépendantAlibaba Cloud · Stable2026-07-15Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.3Valeur · Estimated53.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEntrée vectorielle · par million de Tokens136 987 points
Qwen-Audio-3.0-Realtime-Flash
qwen-audio-3.0-realtime-flashModèle indépendantQwen · Stable2026-07-14Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Audio-3.0-Realtime-Plus
qwen-audio-3.0-realtime-plusModèle indépendantQwen · Stable2026-07-14Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT-5.6 Luna
Vérification en attente (UTC+8)
gpt-5.6-lunaModèle indépendantOpenAI · Stable2026-07-09Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated63.7Valeur · Estimated65.5
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 4/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 54.0 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentUsage entrée · par million de Tokens400 000 pointsLecture du cache · par million de Tokens40 000 pointsUsage écriture cache · par million de Tokens500 000 pointsUsage sortie · par million de Tokens2 400 000 points
GPT-5.6 Sol
Vérification en attente (UTC+8)
gpt-5.6-solModèle indépendantOpenAI · Stable2026-07-09Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated83.1Valeur · Estimated67.0
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 77.4 (estimated) · 4/19 observed / reasoning 89.4 (estimated) · 4/13 observed / writing 82.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentUsage entrée · par million de Tokens8 000 000 pointsLecture du cache · par million de Tokens800 000 pointsUsage écriture cache · par million de Tokens10 000 000 pointsUsage sortie · par million de Tokens40 000 000 points
GPT-5.6 Terra
Vérification en attente (UTC+8)
gpt-5.6-terraModèle indépendantOpenAI · Stable2026-07-09Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated73.1Valeur · Estimated62.5
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.0 (estimated) · 4/19 observed / reasoning 85.1 (estimated) · 4/13 observed / writing 69.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentUsage entrée · par million de Tokens4 000 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage écriture cache · par million de Tokens5 000 000 pointsUsage sortie · par million de Tokens24 000 000 points
gpt-live-1
gpt-live-1Modèle indépendantOpenAI · Stable2026-07-08Pas de prix fixe ; facturation selon le servicePerformance · Estimated48.3Valeur · Estimated48.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.4 (estimated) · 0/19 observed / reasoning 52.2 (estimated) · 0/13 observed / writing 41.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: gpt-4-0125-preview · 10 benchmarksReference: gpt-4-1106-preview · 10 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4o · 7 benchmarksReference: gpt-5.2 · 7 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT Realtime 2.1
Vérification en attente (UTC+8)
gpt-realtime-2.1Modèle indépendantOpenAI · Aperçu2026-07-06Voix et texte en temps réel disponibles. Images et exécution d’outils pendant l’appel non activées.Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated45.3Valeur · Estimated31.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · OfficialUsage entrée · par million de Tokens8 000 000 pointsLecture du cache · par million de Tokens800 000 pointsUsage sortie · par million de Tokens48 000 000 pointsUsage entrée · Image · par million de Tokens10 000 000 pointsLecture du cache · Image · par million de Tokens1 000 000 pointsUsage entrée · Audio · par million de Tokens64 000 000 pointsLecture du cache · Audio · par million de Tokens800 000 pointsUsage sortie · Audio · par million de Tokens128 000 000 points
GPT Realtime 2.1 Mini
Vérification en attente (UTC+8)
gpt-realtime-2.1-miniModèle indépendantOpenAI · Aperçu2026-07-06Voix et texte en temps réel disponibles. Images et exécution d’outils pendant l’appel non activées.Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated45.3Valeur · Estimated61.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · OfficialUsage entrée · par million de Tokens1 200 000 pointsLecture du cache · par million de Tokens120 000 pointsUsage sortie · par million de Tokens4 800 000 pointsUsage entrée · Image · par million de Tokens1 600 000 pointsLecture du cache · Image · par million de Tokens160 000 pointsUsage entrée · Audio · par million de Tokens20 000 000 pointsLecture du cache · Audio · par million de Tokens600 000 pointsUsage sortie · Audio · par million de Tokens40 000 000 points
Qwen-Audio-3.0-TTS-Flash
Vérification en attente (UTC+8)
qwen-audio-3.0-tts-flashModèle indépendantAlibaba Cloud · Stable2026-07 (mois officiel uniquement)Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated74.4Valeur · Estimated74.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · OfficialAudio · pour 10 000 caractères273 973 points
Qwen-Audio-3.0-TTS-Plus
Vérification en attente (UTC+8)
qwen-audio-3.0-tts-plusModèle indépendantAlibaba Cloud · Stable2026-07 (mois officiel uniquement)Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated74.4Valeur · Estimated63.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · OfficialAudio · pour 10 000 caractères383 562 points
claude-sonnet-5
claude-sonnet-5Modèle indépendantAnthropic · Stable2026-06-30Pas de prix fixe ; facturation selon le servicePerformance · Estimated70.2Valeur · Estimated64.1
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.0 (estimated) · 5/19 observed / reasoning 76.6 (estimated) · 4/13 observed / writing 58.1 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
claude-sonnet-5-100
claude-sonnet-5-100Modèle indépendantAnthropic · Stable2026-06-30Pas de prix fixe ; facturation selon le servicePerformance · Estimated70.2Valeur · Estimated64.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.0 (estimated) · 0/19 observed / reasoning 76.6 (estimated) · 0/13 observed / writing 58.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-sonnet-5-5-100 by 4.2 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Doubao Seed 2.1 Turbo (2026-06-28)
Vérification en attente (UTC+8)
doubao-seed-2-1-turbo-260628Instantané / version fixe · Accès uniqueByteDance · Stable2026-06-28Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated57.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens821 918 pointsLecture du cache · par million de Tokens164 384 pointsUsage sortie · par million de Tokens4 109 589 points
Mistral OCR 4
Vérification en attente (UTC+8)
mistral-ocr-4-0Modèle indépendantMistral AI · Aperçu2026-06-23Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance81.8Valeur57.3
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 25%mistral-ocr · Officialcohere-parsebench · OfficialTraitement documentaire · par 1 000 pages8 000 000 pointsDocuments avec annotations structurées · par 1 000 pages10 000 000 points
HappyHorse-1.1-I2V
Vérification en attente (UTC+8)
happyhorse-1.1-i2vModèle indépendantAlibaba Cloud · Stable2026-06-22Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated80.9Valeur · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentGénération vidéo 480P · par seconde123 288 pointsGénération vidéo 720P · par seconde246 576 pointsGénération vidéo 1080P · par seconde328 768 points
HappyHorse-1.1-R2V
Vérification en attente (UTC+8)
happyhorse-1.1-r2vModèle indépendantAlibaba Cloud · Stable2026-06-22Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated80.9Valeur · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentGénération vidéo 480P · par seconde123 288 pointsGénération vidéo 720P · par seconde246 576 pointsGénération vidéo 1080P · par seconde328 768 points
HappyHorse-1.1-T2V
Vérification en attente (UTC+8)
happyhorse-1.1-t2vModèle indépendantAlibaba Cloud · Stable2026-06-22Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated80.9Valeur · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentGénération vidéo 480P · par seconde123 288 pointsGénération vidéo 720P · par seconde246 576 pointsGénération vidéo 1080P · par seconde328 768 points
doubao-GLM 5.2 (2026-06-17)
Vérification en attente (UTC+8)
doubao-glm-5-2-260617Instantané / version fixe · Accès uniqueZhipu · Stable2026-06-17Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated54.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens7 671 233 points
qwen-HappyOyster-1.0-Adventure
qwen-happyoyster-1.0-adventureModèle indépendanthappyoyster · Stable2026-06-17Pas de prix fixe ; facturation selon le servicePerformance · Estimated43.2Valeur · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GLM-5.2
Vérification en attente (UTC+8)
glm-5.2Modèle indépendantZhipu · Stable2026-06-16Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated66.4Valeur · Estimated61.3
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 68.8 (estimated) · 5/19 observed / reasoning 70.9 (estimated) · 4/13 observed / writing 59.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens7 671 233 points
Qwen3.5-OCR
Vérification en attente (UTC+8)
qwen3.5-ocrModèle indépendantAlibaba Cloud · Stable2026-06-16Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated81.8Valeur · Estimated72.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · OfficialUsage entrée · par million de Tokens136 987 pointsUsage sortie · par million de Tokens547 946 points
qwen-GLM-5.2
Vérification en attente (UTC+8)
qwen-glm-5.2Modèle indépendantZhipu · Stable2026-06-16Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated61.1Valeur · Estimated57.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens7 671 233 points
qwen-pixverse/pixverse-upscale
qwen-pixverse-pixverse-upscaleModèle indépendantpixverse · Stable2026-06-16Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ZHIPU/GLM-5.2
Vérification en attente (UTC+8)
qwen-zhipu-glm-5.2Modèle indépendantZhipu AI · Stable2026-06-16Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens7 671 233 points
qwen-kimi-k2.7-code
Vérification en attente (UTC+8)
qwen-kimi-k2.7-codeModèle indépendantMoonshot · Stable2026-06-15Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated34.7Valeur · Estimated39.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.4 (estimated) · 0/13 observed / writing 28.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 780 822 pointsLecture du cache · par million de Tokens356 164 pointsUsage sortie · par million de Tokens7 397 260 points
Kimi K2.7 Code
Vérification en attente (UTC+8)
kimi-k2.7-codeModèle indépendantMoonshot · Stable2026-06-12Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated46.3Valeur · Estimated47.8
8/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.8 (estimated) · 3/19 observed / reasoning 48.4 (estimated) · 3/13 observed / writing 42.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · IndependentUsage entrée · par million de Tokens1 780 822 pointsLecture du cache · par million de Tokens356 164 pointsUsage sortie · par million de Tokens7 397 260 points
qwen-kimi/kimi-k2.7-code
Vérification en attente (UTC+8)
qwen-kimi-kimi-k2.7-codeModèle indépendantMoonshot AI · Stable2026-06-12Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated29.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 780 822 pointsLecture du cache · par million de Tokens356 164 pointsUsage sortie · par million de Tokens7 397 260 points
claude-fable-5
claude-fable-5Modèle indépendantAnthropic · Stable2026-06-09Pas de prix fixe ; facturation selon le servicePerformance · Estimated87.7Valeur · Estimated76.4
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.6 (estimated) · 5/19 observed / reasoning 90.7 (estimated) · 4/13 observed / writing 86.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
claude-fable-5-100
claude-fable-5-100Modèle indépendantAnthropic · Stable2026-06-09Pas de prix fixe ; facturation selon le servicePerformance · Estimated87.7Valeur · Estimated76.4
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.6 (estimated) · 0/19 observed / reasoning 90.7 (estimated) · 0/13 observed / writing 86.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-fable-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-fable-5-1-100 by 1.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3.7-Max-2026-06-08
Vérification en attente (UTC+8)
qwen3.7-max-2026-06-08Instantané / version fixe · Accès uniqueQwen · Stable2026-06-09Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated64.5Valeur · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 0/19 observed / reasoning 69.6 (estimated) · 0/13 observed / writing 73.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: qwen3.7-max-preview · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens3 287 671 pointsLecture du cache · par million de Tokens657 534 pointsUsage sortie · par million de Tokens9 863 014 points
doubao-seedance-2-5-260628
Vérification en attente (UTC+8)
doubao-seedance-2-5-260628Instantané / version fixe · Accès uniqueByteDance · Stable2026-06 (mois officiel uniquement)Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated90.4Valeur · Estimated63.3
Version comparison reviewEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.5-720p · 90.4Review: below doubao-seedance-2-0-260128 by 1.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · IndependentUsage sortie · Génération vidéo · par million de Tokens19 178 083 points
doubao-seed-evolving
doubao-seed-evolvingAlias · Accès uniqueDoubao · Stable2026-06 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
doubao-seedream-5-0-pro-260628
Vérification en attente (UTC+8)
doubao-seedream-5-0-pro-260628Instantané / version fixe · Accès uniqueByteDance · Stable2026-06 (mois officiel uniquement)Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated85.2Valeur · Estimated69.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-5.0-pro · 85.2arena · Independentarena · IndependentUsage sortie · Image · par image82 192 pointsUsage entrée · Image · par image5 480 points
Fun-ASR-Flash-2026-06-15
Vérification en attente (UTC+8)
fun-asr-flash-2026-06-15Instantané / version fixe · Accès uniqueAlibaba Cloud · Stable2026-06 (mois officiel uniquement)Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.4Valeur · Estimated94.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · par seconde61 points
Qwen3.7-Plus
Vérification en attente (UTC+8)
qwen3.7-plusModèle indépendantQwen · Stable2026-06-01Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.0Valeur · Estimated60.5
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.7 (estimated) · 2/19 observed / reasoning 62.0 (estimated) · 1/13 observed / writing 55.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 256 000 TokenUsage entrée · par million de Tokens438 356 pointsLecture du cache · par million de Tokens87 671 pointsUsage sortie · par million de Tokens1 753 425 points
Input 256 001+ TokenUsage entrée · par million de Tokens1 315 068 pointsLecture du cache · par million de Tokens263 014 pointsUsage sortie · par million de Tokens5 260 274 points
qwen-MiniMax/MiniMax-M3
Vérification en attente (UTC+8)
qwen-minimax-minimax-m3Modèle indépendantmini-max · Stable2026-06-01Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated46.0
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-thinking-2507 · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksReview: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 150 685 pointsLecture du cache · par million de Tokens230 137 pointsUsage sortie · par million de Tokens4 602 740 points
qwen-stepfun/step-3.7-flash
Vérification en attente (UTC+8)
qwen-stepfun-step-3.7-flashModèle indépendantstepfun · Stable2026-05-29Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated61.4Valeur · Estimated64.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens369 863 pointsLecture du cache · par million de Tokens73 973 pointsUsage sortie · par million de Tokens2 219 178 points
claude-opus-4-8
claude-opus-4-8Modèle indépendantAnthropic · Stable2026-05-28Pas de prix fixe ; facturation selon le servicePerformance · Estimated74.3Valeur · Estimated67.0
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 72.3 (estimated) · 5/19 observed / reasoning 77.9 (estimated) · 4/13 observed / writing 72.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
claude-opus-4-8-100
claude-opus-4-8-100Modèle indépendantAnthropic · Stable2026-05-28Pas de prix fixe ; facturation selon le servicePerformance · Estimated74.3Valeur · Estimated67.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 72.3 (estimated) · 0/19 observed / reasoning 77.9 (estimated) · 0/13 observed / writing 72.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-8 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3.7-Max
Vérification en attente (UTC+8)
qwen3.7-maxModèle indépendantQwen · Stable2026-05-21Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated64.5Valeur · Estimated58.6
8/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 3/19 observed / reasoning 69.6 (estimated) · 3/13 observed / writing 73.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max-preview · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarkslivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · IndependentUsage entrée · par million de Tokens3 287 671 pointsLecture du cache · par million de Tokens657 534 pointsUsage sortie · par million de Tokens9 863 014 points
Cohere Command A Plus
Vérification en attente (UTC+8)
cohere-command-a-plus-05-2026Modèle indépendantCohere · Aperçu2026-05-20Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated55.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 600 000 pointsUsage sortie · par million de Tokens6 400 000 points
Qwen3.7-Max-Preview
Vérification en attente (UTC+8)
qwen3.7-max-previewModèle indépendantQwen · Aperçu2026-05-20Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated64.5Valeur · Estimated58.6
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 1/19 observed / reasoning 69.6 (estimated) · 1/13 observed / writing 73.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens3 287 671 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens9 863 014 points
Qwen3.5-LiveTranslate-Flash-Realtime
qwen3.5-livetranslate-flash-realtimeModèle indépendantQwen · Stable2026-05-19Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Grok 4.3
Vérification en attente (UTC+8)
grok-4.3Modèle indépendantxAI · Aperçu2026-05-12Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated44.8Valeur · Estimated46.5
Shared exact-model performance from grok-4.3; coverage refers to public model benchmarks, not tests of every platform deployment.12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.8 (estimated) · 4/19 observed / reasoning 48.3 (estimated) · 4/13 observed / writing 47.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentUsage entrée · par million de Tokens2 500 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage sortie · par million de Tokens5 000 000 points
Mistral Medium 3.5
Vérification en attente (UTC+8)
mistral-medium-3-5Modèle indépendantMistral AI · Aperçu2026-04-28Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated60.6Valeur · Estimated55.3
6/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 3/19 observed / reasoning 70.3 (estimated) · 1/13 observed / writing 61.1 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independentarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officiallivebench · IndependentUsage entrée · par million de Tokens3 000 000 pointsUsage sortie · par million de Tokens15 000 000 points
HappyHorse-1.0-I2V
Vérification en attente (UTC+8)
happyhorse-1.0-i2vModèle indépendantAlibaba Cloud · Stable2026-04-27Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated80.9Valeur · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentGénération vidéo 720P · par seconde246 576 pointsGénération vidéo 1080P · par seconde438 357 points
HappyHorse-1.0-R2V
Vérification en attente (UTC+8)
happyhorse-1.0-r2vModèle indépendantAlibaba Cloud · Stable2026-04-27Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated80.9Valeur · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentGénération vidéo 720P · par seconde246 576 pointsGénération vidéo 1080P · par seconde438 357 points
HappyHorse-1.0-T2V
Vérification en attente (UTC+8)
happyhorse-1.0-t2vModèle indépendantAlibaba Cloud · Stable2026-04-27Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated80.9Valeur · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentGénération vidéo 720P · par seconde246 576 pointsGénération vidéo 1080P · par seconde438 357 points
qwen-DeepSeek-V4-Pro
Vérification en attente (UTC+8)
qwen-deepseek-v4-proModèle indépendantDeepSeek · Stable2026-04-24Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated70.1Valeur · Estimated63.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.8 (estimated) · 0/19 observed / reasoning 74.5 (estimated) · 0/13 observed / writing 69.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-27b · 13 benchmarksReference: qwen3.8-max · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens3 287 671 pointsLecture du cache · par million de Tokens273 973 pointsUsage sortie · par million de Tokens6 575 342 points
GPT-5.5
Vérification en attente (UTC+8)
gpt-5.5Modèle indépendantOpenAI · Stable2026-04-23Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated80.5Valeur · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 71.8 (estimated) · 4/19 observed / reasoning 88.6 (estimated) · 4/13 observed / writing 81.1 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.5 (codex-harness) · 1 benchmarksReference: gpt-5.5-high (codex-harness) · 1 benchmarksReference: gpt-5.5-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentUsage entrée · par million de Tokens10 000 000 pointsLecture du cache · par million de Tokens1 000 000 pointsUsage sortie · par million de Tokens60 000 000 points
qwen-xiaomi/mimo-v2.5-pro
Vérification en attente (UTC+8)
qwen-xiaomi-mimo-v2.5-proModèle indépendantXiaomi · Stable2026-04-23Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated30.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 917 808 pointsLecture du cache · par million de Tokens383 562 pointsUsage sortie · par million de Tokens5 753 425 points
Qwen3.6-27B
Vérification en attente (UTC+8)
qwen3.6-27bModèle indépendantQwen · Stable2026-04-22Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated46.6Valeur · Estimated50.5
7/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 40.1 (estimated) · 2/19 observed / reasoning 56.9 (estimated) · 3/13 observed / writing 42.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.5-122b-a10b · 5 benchmarksReference: qwen3.5-27b · 5 benchmarksReference: qwen3.5-397b-a17b · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarkslivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · IndependentUsage entrée · par million de Tokens821 918 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens4 931 507 points
GPT Image 2
Vérification en attente (UTC+8)
gpt-image-2Modèle indépendantOpenAI · Stable2026-04-21Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance97.0Valeur69.3
Usage entrée · par million de Tokens10 000 000 pointsLecture du cache · par million de Tokens2 500 000 pointsUsage entrée · Image · par million de Tokens16 000 000 pointsLecture du cache · Image · par million de Tokens4 000 000 pointsUsage sortie · Image · par million de Tokens60 000 000 points
qwen-Kimi-K2.6
Vérification en attente (UTC+8)
qwen-kimi-k2.6Modèle indépendantMoonshot · Stable2026-04-21Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated34.9Valeur · Estimated39.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 780 822 pointsLecture du cache · par million de Tokens356 164 pointsUsage sortie · par million de Tokens7 397 260 points
Kimi K2.6
Vérification en attente (UTC+8)
kimi-k2.6Modèle indépendantMoonshot · Stable2026-04-20Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated77.4Valeur · Estimated69.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 77.8 (estimated) · 2/19 observed / reasoning 78.7 (estimated) · 1/13 observed / writing 75.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: kimi-k3 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 780 822 pointsLecture du cache · par million de Tokens301 370 pointsUsage sortie · par million de Tokens7 397 260 points
qwen-Kimi/Kimi K2.6
Vérification en attente (UTC+8)
qwen-kimi-kimi-k2.6Modèle indépendantMoonshot AI · Stable2026-04-20Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 780 822 pointsLecture du cache · par million de Tokens301 370 pointsUsage sortie · par million de Tokens7 397 260 points
claude-opus-4-7
claude-opus-4-7Modèle indépendantAnthropic · Stable2026-04-16Pas de prix fixe ; facturation selon le servicePerformance · Estimated74.1Valeur · Estimated66.9
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.6 (estimated) · 4/19 observed / reasoning 81.7 (estimated) · 4/13 observed / writing 67.0 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
claude-opus-4-7-100
claude-opus-4-7-100Modèle indépendantAnthropic · Stable2026-04-16Pas de prix fixe ; facturation selon le servicePerformance · Estimated74.1Valeur · Estimated66.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.6 (estimated) · 0/19 observed / reasoning 81.7 (estimated) · 0/13 observed / writing 67.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-7 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3.6-35B-A3B
Vérification en attente (UTC+8)
qwen3.6-35b-a3bModèle indépendantQwen · Stable2026-04-16Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated45.4Valeur · Estimated51.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.0 (estimated) · 0/19 observed / reasoning 54.8 (estimated) · 0/13 observed / writing 42.3 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.5-122b-a10b · 5 benchmarksReference: qwen3.5-35b-a3b · 5 benchmarksReference: qwen3.5-397b-a17b · 5 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens493 151 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens2 958 904 points
Qwen3.6-Flash
Vérification en attente (UTC+8)
qwen3.6-flashModèle indépendantQwen · Stable2026-04-16Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated58.2Valeur · Estimated62.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 256 000 TokenUsage entrée · par million de Tokens328 767 pointsLecture du cache · par million de Tokens65 753 pointsUsage sortie · par million de Tokens1 972 603 points
Input 256 001+ TokenUsage entrée · par million de Tokens1 315 068 pointsLecture du cache · par million de Tokens263 014 pointsUsage sortie · par million de Tokens7 890 411 points
qwen-GLM-5.1
Vérification en attente (UTC+8)
qwen-glm-5.1Modèle indépendantZhipu · Stable2026-04-14Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated61.1Valeur · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32 000 TokenUsage entrée · par million de Tokens1 643 836 pointsLecture du cache · par million de Tokens328 767 pointsUsage sortie · par million de Tokens6 575 342 points
Input 32 001+ TokenUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens438 356 pointsUsage sortie · par million de Tokens7 671 233 points
qwen-ViduQ3-mix_reference2video
qwen-vidu-viduq3-mix_reference2videoModèle indépendantvidu · Stable2026-04-13Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3_reference2video
qwen-vidu-viduq3_reference2videoModèle indépendantvidu · Stable2026-04-13Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-Turbo_reference2video
qwen-vidu-viduq3-turbo_reference2videoModèle indépendantvidu · Stable2026-04-13Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-PixVerse-C1-it2v
qwen-pixverse-pixverse-c1-it2vModèle indépendantpixverse · Stable2026-04-07Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-PixVerse-C1-kf2v
qwen-pixverse-pixverse-c1-kf2vModèle indépendantpixverse · Stable2026-04-07Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-PixVerse-C1-r2v
qwen-pixverse-pixverse-c1-r2vModèle indépendantpixverse · Stable2026-04-07Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-PixVerse-C1-t2v
qwen-pixverse-pixverse-c1-t2vModèle indépendantpixverse · Stable2026-04-07Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ZHIPU/GLM-5.1
Vérification en attente (UTC+8)
qwen-zhipu-glm-5.1Modèle indépendantZhipu AI · Stable2026-04-07Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens7 671 233 points
Wan2.7-I2V
Vérification en attente (UTC+8)
wan2.7-i2vModèle indépendantAlibaba Cloud · Stable2026-04-07Dernière vérification du prixVérification en attente (UTC+8)
Performance78.7Valeur63.2
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGénération vidéo 720P · par seconde164 384 pointsGénération vidéo 1080P · par seconde273 973 points
Wan2.7-R2V
Vérification en attente (UTC+8)
wan2.7-r2vModèle indépendantAlibaba Cloud · Stable2026-04-07Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated69.2Valeur · Estimated56.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-i2v · 78.7Reference: wan2.7-t2v · 59.6arena · Independentarena · IndependentGénération vidéo 720P · par seconde164 384 pointsGénération vidéo 1080P · par seconde273 973 points
Wan2.7-T2V
Vérification en attente (UTC+8)
wan2.7-t2vModèle indépendantAlibaba Cloud · Stable2026-04-07Dernière vérification du prixVérification en attente (UTC+8)
Performance59.6Valeur49.8
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGénération vidéo 720P · par seconde164 384 pointsGénération vidéo 1080P · par seconde273 973 points
qwen-Wan2.7-VideoEdit
wan2.7-videoeditModèle indépendantWan · Stable2026-04-07Pas de prix fixe ; facturation selon le servicePerformance · Estimated69.2Valeur · Estimated63.4
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-i2v · 78.7Reference: wan2.7-t2v · 59.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Grok 4.20 Non-Reasoning
Vérification en attente (UTC+8)
grok-4-20-non-reasoningModèle indépendantxAI · Aperçu2026-04-06Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated54.7
Shared exact-model performance from grok-4-20-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 500 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage sortie · par million de Tokens5 000 000 points
Grok 4.20 Reasoning
Vérification en attente (UTC+8)
grok-4-20-reasoningModèle indépendantxAI · Aperçu2026-04-06Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated54.7
Shared exact-model performance from grok-4-20-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 500 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage sortie · par million de Tokens5 000 000 points
Gemma 4 26B A4B It-100
Vérification en attente (UTC+8)
gemma-4-26b-a4b-it-maas-001Modèle indépendantGoogle · Aperçu2026-04-02Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated62.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens300 000 pointsLecture du cache · par million de Tokens30 000 pointsUsage sortie · par million de Tokens1 200 000 points
Veo 3.1 Lite Generate 001-100
veo-3.1-lite-generate-001Modèle indépendantGoogle · Stable2026-04-02Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
doubao-seed3d-2-0-260328
Vérification en attente (UTC+8)
doubao-seed3d-2-0-260328Instantané / version fixe · Accès uniqueByteDance · Stable2026-04 (mois officiel uniquement)Dernière vérification du prixVérification en attente (UTC+8)
Performance82.2Valeur57.5
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 18%seed3d-public · OfficialUsage sortie · 3D · par million de Tokens21 917 809 points
Qwen3.6-Plus
Vérification en attente (UTC+8)
qwen3.6-plusModèle indépendantQwen · Stable2026-04-01Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated54.5Valeur · Estimated57.7
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 4/19 observed / reasoning 60.4 (estimated) · 4/13 observed / writing 52.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput 0 – 256 000 TokenUsage entrée · par million de Tokens547 945 pointsLecture du cache · par million de Tokens109 589 pointsUsage sortie · par million de Tokens3 287 671 points
Input 256 001+ TokenUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens438 356 pointsUsage sortie · par million de Tokens13 150 685 points
Wan2.7-Image
Vérification en attente (UTC+8)
wan2.7-imageModèle indépendantAlibaba Cloud · Stable2026-04-01Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance41.7Valeur46.3
Version comparison reviewProvisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%Review: below wan2.6-t2i by 8.3 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · IndependentUsage sortie · Image · par image54 795 points
Wan2.7-Image-Pro
Vérification en attente (UTC+8)
wan2.7-image-proModèle indépendantAlibaba Cloud · Stable2026-04-01Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance44.1Valeur30.9
Usage sortie · Image · par image136 987 points
qwen-PixVerse-V6-it2v
qwen-pixverse-pixverse-v6-it2vModèle indépendantpixverse · Stable2026-03-29Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-PixVerse-V6-kf2v
qwen-pixverse-pixverse-v6-kf2vModèle indépendantpixverse · Stable2026-03-29Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-PixVerse-V6-t2v
qwen-pixverse-pixverse-v6-t2vModèle indépendantpixverse · Stable2026-03-29Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GLM-5.1
Vérification en attente (UTC+8)
glm-5.1Modèle indépendantZhipu · Stable2026-03-27Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated65.1Valeur · Estimated61.4
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.7 (estimated) · 2/19 observed / reasoning 69.9 (estimated) · 1/13 observed / writing 58.6 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 31 999 TokenUsage entrée · par million de Tokens1 643 836 pointsLecture du cache · par million de Tokens356 164 pointsUsage sortie · par million de Tokens6 575 342 points
Input 32 000+ TokenUsage entrée · par million de Tokens2 191 781 pointsLecture du cache · par million de Tokens547 945 pointsUsage sortie · par million de Tokens7 671 233 points
Lyria 3 Clip Preview-100
lyria-3-clip-previewModèle indépendantGoogle · Stable2026-03-25Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Lyria 3 Pro Preview-100
lyria-3-pro-previewModèle indépendantGoogle · Stable2026-03-25Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-MiniMax/MiniMax-M2.7
Vérification en attente (UTC+8)
qwen-minimax-minimax-m2.7Modèle indépendantMiniMax · Stable2026-03-18Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens575 342 pointsLecture du cache · par million de Tokens115 068 pointsUsage sortie · par million de Tokens2 301 370 points
GPT-5.4 Mini
Vérification en attente (UTC+8)
gpt-5.4-miniModèle indépendantOpenAI · Stable2026-03-17Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated47.9Valeur · Estimated48.9
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 44.3 (estimated) · 4/19 observed / reasoning 53.8 (estimated) · 4/13 observed / writing 45.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentUsage entrée · par million de Tokens1 500 000 pointsLecture du cache · par million de Tokens150 000 pointsUsage sortie · par million de Tokens9 000 000 points
GPT-5.4 Nano
Vérification en attente (UTC+8)
gpt-5.4-nanoModèle indépendantOpenAI · Stable2026-03-17Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated48.6Valeur · Estimated54.8
11/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 44.5 (estimated) · 3/19 observed / reasoning 57.0 (estimated) · 4/13 observed / writing 44.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-nano-2025-04-14 · 7 benchmarksReference: gpt-5.4 · 2 benchmarksReference: gpt-5.4-high (codex-harness) · 1 benchmarksReference: gpt-5.4-mini · 1 benchmarksarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · IndependentUsage entrée · par million de Tokens400 000 pointsLecture du cache · par million de Tokens40 000 pointsUsage sortie · par million de Tokens2 500 000 points
GLM-5-Turbo
Vérification en attente (UTC+8)
glm-5-turboModèle indépendantZhipu · Stable2026-03-14Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated56.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 31 999 TokenUsage entrée · par million de Tokens1 369 863 pointsLecture du cache · par million de Tokens328 767 pointsUsage sortie · par million de Tokens6 027 397 points
Input 32 000+ TokenUsage entrée · par million de Tokens1 917 808 pointsLecture du cache · par million de Tokens493 151 pointsUsage sortie · par million de Tokens7 123 288 points
qwen-Tripo-P1.0
qwen-tripo-tripo-p1.0Modèle indépendanttripo · Stable2026-03-11Pas de prix fixe ; facturation selon le servicePerformance · Estimated43.2Valeur · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Tripo-H3.1
qwen-tripo-tripo-h3.1Modèle indépendanttripo · Stable2026-03-06Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.9Valeur · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT-5.4
Vérification en attente (UTC+8)
gpt-5.4Modèle indépendantOpenAI · Stable2026-03-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated73.0Valeur · Estimated61.5
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.7 (estimated) · 5/19 observed / reasoning 84.9 (estimated) · 4/13 observed / writing 75.5 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialUsage entrée · par million de Tokens5 000 000 pointsLecture du cache · par million de Tokens500 000 pointsUsage sortie · par million de Tokens30 000 000 points
GPT-5.4 Pro
Vérification en attente (UTC+8)
gpt-5.4-proModèle indépendantOpenAI · Stable2026-03-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated58.8Valeur · Estimated41.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 49.8 (estimated) · 0/19 observed / reasoning 67.8 (estimated) · 0/13 observed / writing 58.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-5.4 · 13 benchmarksReference: gpt-5.4-mini · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: gpt-5.4-nano · 11 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens60 000 000 pointsUsage sortie · par million de Tokens360 000 000 points
Qwen3.5-Omni-Flash
qwen3.5-omni-flashModèle indépendantQwen · Stable2026-03 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated58.2Valeur · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3.5-Omni-Flash-Realtime
qwen3.5-omni-flash-realtimeModèle indépendantQwen · Stable2026-03 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3.5-Omni-Plus
qwen3.5-omni-plusModèle indépendantQwen · Stable2026-03 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated54.5Valeur · Estimated53.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 0/19 observed / reasoning 60.4 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3.5-Omni-Plus-Realtime
qwen3.5-omni-plus-realtimeModèle indépendantQwen · Stable2026-03 (mois officiel uniquement)Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-pixverse/pixverse-motioncontrol
qwen-pixverse-pixverse-motioncontrolModèle indépendantpixverse · Stable2026-02-28Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT-5.3 Codex
Vérification en attente (UTC+8)
gpt-5.3-codexModèle indépendantOpenAI · Stable2026-02-24Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated58.5Valeur · Estimated52.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.4 (estimated) · 0/19 observed / reasoning 63.1 (estimated) · 0/13 observed / writing 56.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-5.4 · 9 benchmarksReference: gpt-5.2 · 8 benchmarksReference: gpt-5.2-codex · 8 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.2-codex by 3.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens3 500 000 pointsLecture du cache · par million de Tokens350 000 pointsUsage sortie · par million de Tokens28 000 000 points
qwen-MiniMax-M2.5
Vérification en attente (UTC+8)
qwen-minimax-m2.5Modèle indépendantMiniMax · Stable2026-02-24Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated34.9Valeur · Estimated44.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens575 342 pointsLecture du cache · par million de Tokens115 068 pointsUsage sortie · par million de Tokens2 301 370 points
GPT Audio 1.5
Vérification en attente (UTC+8)
gpt-audio-1.5Modèle indépendantOpenAI · Stable2026-02-23Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated52.6Valeur · Estimated41.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · OfficialUsage entrée · par million de Tokens5 000 000 pointsUsage sortie · par million de Tokens20 000 000 pointsUsage entrée · Audio · par million de Tokens64 000 000 pointsUsage sortie · Audio · par million de Tokens128 000 000 points
GPT Realtime 1.5
Vérification en attente (UTC+8)
gpt-realtime-1.5Modèle indépendantOpenAI · Stable2026-02-23Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated45.3Valeur · Estimated31.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · OfficialUsage entrée · par million de Tokens8 000 000 pointsLecture du cache · par million de Tokens800 000 pointsUsage sortie · par million de Tokens32 000 000 pointsUsage entrée · Image · par million de Tokens10 000 000 pointsLecture du cache · Image · par million de Tokens1 000 000 pointsUsage entrée · Audio · par million de Tokens64 000 000 pointsLecture du cache · Audio · par million de Tokens800 000 pointsUsage sortie · Audio · par million de Tokens128 000 000 points
Qwen3.5-122B-A10B
Vérification en attente (UTC+8)
qwen3.5-122b-a10bModèle indépendantQwen · Stable2026-02-23Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated46.4Valeur · Estimated55.2
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.9 (estimated) · 2/19 observed / reasoning 56.8 (estimated) · 1/13 observed / writing 42.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128 000 TokenUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens1 753 425 points
Input 128 001+ TokenUsage entrée · par million de Tokens547 945 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens4 383 562 points
Qwen3.5-27B
Vérification en attente (UTC+8)
qwen3.5-27bModèle indépendantQwen · Stable2026-02-23Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated45.7Valeur · Estimated55.9
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.4 (estimated) · 2/19 observed / reasoning 56.1 (estimated) · 1/13 observed / writing 41.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128 000 TokenUsage entrée · par million de Tokens164 384 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens1 315 068 points
Input 128 001+ TokenUsage entrée · par million de Tokens493 151 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens3 945 205 points
Qwen3.5-35B-A3B
Vérification en attente (UTC+8)
qwen3.5-35b-a3bModèle indépendantQwen · Stable2026-02-23Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated42.9Valeur · Estimated55.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.8 (estimated) · 2/19 observed / reasoning 51.7 (estimated) · 1/13 observed / writing 40.2 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128 000 TokenUsage entrée · par million de Tokens109 589 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens876 712 points
Input 128 001+ TokenUsage entrée · par million de Tokens438 356 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens3 506 849 points
Qwen3.5-Flash
Vérification en attente (UTC+8)
qwen3.5-flashModèle indépendantQwen · Stable2026-02-23Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated58.2Valeur · Estimated68.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 2/19 observed / reasoning 62.8 (estimated) · 1/13 observed / writing 59.9 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128 000 TokenUsage entrée · par million de Tokens54 795 pointsLecture du cache · par million de Tokens10 959 pointsUsage sortie · par million de Tokens547 945 points
Input 128 001 – 256 000 TokenUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens43 836 pointsUsage sortie · par million de Tokens2 191 781 points
Input 256 001+ TokenUsage entrée · par million de Tokens328 767 pointsLecture du cache · par million de Tokens65 753 pointsUsage sortie · par million de Tokens3 287 671 points
qwen-GLM-5
Vérification en attente (UTC+8)
qwen-glm-5Modèle indépendantZhipu · Stable2026-02-18Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated61.1Valeur · Estimated60.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32 000 TokenUsage entrée · par million de Tokens1 095 890 pointsLecture du cache · par million de Tokens219 178 pointsUsage sortie · par million de Tokens4 931 507 points
Input 32 001+ TokenUsage entrée · par million de Tokens1 643 836 pointsLecture du cache · par million de Tokens328 767 pointsUsage sortie · par million de Tokens6 027 397 points
claude-sonnet-4-6
claude-sonnet-4-6Modèle indépendantAnthropic · Stable2026-02-17Pas de prix fixe ; facturation selon le servicePerformance · Estimated65.2Valeur · Estimated60.6
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.0 (estimated) · 4/19 observed / reasoning 71.9 (estimated) · 4/13 observed / writing 59.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
claude-sonnet-4-6-100
claude-sonnet-4-6-100Modèle indépendantAnthropic · Stable2026-02-17Pas de prix fixe ; facturation selon le servicePerformance · Estimated65.2Valeur · Estimated60.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.0 (estimated) · 0/19 observed / reasoning 71.9 (estimated) · 0/13 observed / writing 59.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-4-6 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3.5-397B-A17B
Vérification en attente (UTC+8)
qwen3.5-397b-a17bModèle indépendantQwen · Stable2026-02-15Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated49.6Valeur · Estimated56.4
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 42.6 (estimated) · 2/19 observed / reasoning 59.5 (estimated) · 1/13 observed / writing 46.6 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128 000 TokenUsage entrée · par million de Tokens328 767 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens1 972 603 points
Input 128 001+ TokenUsage entrée · par million de Tokens821 918 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens4 931 507 points
Qwen3.5-Plus
Vérification en attente (UTC+8)
qwen3.5-plusModèle indépendantQwen · Stable2026-02-15Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated54.5Valeur · Estimated61.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 0/19 observed / reasoning 60.4 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 128 000 TokenUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens43 836 pointsUsage sortie · par million de Tokens1 315 068 points
Input 128 001 – 256 000 TokenUsage entrée · par million de Tokens547 945 pointsLecture du cache · par million de Tokens109 589 pointsUsage sortie · par million de Tokens3 287 671 points
Input 256 001+ TokenUsage entrée · par million de Tokens1 095 890 pointsLecture du cache · par million de Tokens219 178 pointsUsage sortie · par million de Tokens6 575 342 points
qwen-MiniMax/MiniMax-M2.5
Vérification en attente (UTC+8)
qwen-minimax-minimax-m2.5Modèle indépendantMiniMax · Stable2026-02-12Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens575 342 pointsLecture du cache · par million de Tokens57 534 pointsUsage sortie · par million de Tokens2 301 370 points
qwen-PixVerse-V5.6-r2v
qwen-pixverse-pixverse-v5.6-r2vModèle indépendantpixverse · Stable2026-02-12Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ZHIPU/GLM-5
Vérification en attente (UTC+8)
qwen-zhipu-glm-5Modèle indépendantZhipu AI · Stable2026-02-12Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated31.2
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 643 836 pointsLecture du cache · par million de Tokens410 959 pointsUsage sortie · par million de Tokens6 027 397 points
qwen-ViduQ3-Pro_start-end2video
qwen-vidu-viduq3-pro_start-end2videoModèle indépendantvidu · Stable2026-02-11Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-Turbo_img2video
qwen-vidu-viduq3-turbo_img2videoModèle indépendantvidu · Stable2026-02-11Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-Turbo_start-end2video
qwen-vidu-viduq3-turbo_start-end2videoModèle indépendantvidu · Stable2026-02-11Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-Turbo_text2video
qwen-vidu-viduq3-turbo_text2videoModèle indépendantvidu · Stable2026-02-11Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GLM-5
Vérification en attente (UTC+8)
glm-5Modèle indépendantZhipu · Stable2026-02-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.3Valeur · Estimated60.9
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.4 (estimated) · 2/19 observed / reasoning 66.5 (estimated) · 1/13 observed / writing 56.9 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 31 999 TokenUsage entrée · par million de Tokens1 095 890 pointsLecture du cache · par million de Tokens273 973 pointsUsage sortie · par million de Tokens4 931 507 points
Input 32 000+ TokenUsage entrée · par million de Tokens1 643 836 pointsLecture du cache · par million de Tokens410 959 pointsUsage sortie · par million de Tokens6 027 397 points
Qwen-Image-2.0
Vérification en attente (UTC+8)
qwen-image-2.0Modèle indépendantAlibaba Cloud · Stable2026-02-10Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated73.8Valeur · Estimated68.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8arena · Independentarena · IndependentUsage sortie · Image · par image54 795 points
claude-opus-4-6
claude-opus-4-6Modèle indépendantAnthropic · Stable2026-02-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated70.8Valeur · Estimated64.6
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.4 (estimated) · 4/19 observed / reasoning 75.9 (estimated) · 4/13 observed / writing 70.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
claude-opus-4-6-100
claude-opus-4-6-100Modèle indépendantAnthropic · Stable2026-02-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated70.8Valeur · Estimated64.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.4 (estimated) · 0/19 observed / reasoning 75.9 (estimated) · 0/13 observed / writing 70.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-6 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Kling Image 3.0
qwen-kling-kling-v3-image-generationModèle indépendantkling · Stable2026-02-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated73.8Valeur · Estimated66.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Kling Image 3.0 Omni
qwen-kling-kling-v3-omni-image-generationModèle indépendantkling · Stable2026-02-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Kling Video 3.0 Omni
qwen-kling-kling-v3-omni-video-generationModèle indépendantkling · Stable2026-02-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated41.7Valeur · Estimated44.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.7 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 37.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-vl-235b-a22b-instruct · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Kling Video 3.0
qwen-kling-kling-v3-video-generationModèle indépendantkling · Stable2026-02-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Kimi-K2.5
Vérification en attente (UTC+8)
qwen-kimi-k2.5Modèle indépendantMoonshot · Stable2026-01-30Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated34.9Valeur · Estimated41.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 095 890 pointsLecture du cache · par million de Tokens219 178 pointsUsage sortie · par million de Tokens5 753 425 points
Fun-ASR-Flash-8k实时语音识别
fun-asr-flash-8k-realtimeModèle indépendantQwen · Stable2026-01-28Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ2-Pro_reference2video
qwen-vidu-viduq2-pro_reference2videoModèle indépendantvidu · Stable2026-01-27Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-Pro_img2video
qwen-vidu-viduq3-pro_img2videoModèle indépendantvidu · Stable2026-01-27Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-Pro_text2video
qwen-vidu-viduq3-pro_text2videoModèle indépendantvidu · Stable2026-01-27Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3-VL-Plus
Vérification en attente (UTC+8)
qwen3-vl-plusModèle indépendantQwen · Stable2026-01-26Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated42.7Valeur · Estimated51.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.3 (estimated) · 0/19 observed / reasoning 44.7 (estimated) · 0/13 observed / writing 38.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32 000 TokenUsage entrée · par million de Tokens273 973 pointsLecture du cache · par million de Tokens54 795 pointsUsage sortie · par million de Tokens2 739 726 points
Input 32 001 – 128 000 TokenUsage entrée · par million de Tokens410 959 pointsLecture du cache · par million de Tokens82 192 pointsUsage sortie · par million de Tokens4 109 589 points
Input 128 001+ TokenUsage entrée · par million de Tokens821 918 pointsLecture du cache · par million de Tokens164 384 pointsUsage sortie · par million de Tokens8 219 178 points
qwen-PixVerse-V5.6-it2v
qwen-pixverse-pixverse-v5.6-it2vModèle indépendantpixverse · Stable2026-01-26Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-PixVerse-V5.6-kf2v
qwen-pixverse-pixverse-v5.6-kf2vModèle indépendantpixverse · Stable2026-01-26Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-PixVerse-V5.6-t2v
qwen-pixverse-pixverse-v5.6-t2vModèle indépendantpixverse · Stable2026-01-26Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Virtual Try On 001-100
virtual-try-on-001Modèle indépendantGoogle · Stable2026-01-23Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.5Valeur · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT-5.2 Codex
Vérification en attente (UTC+8)
gpt-5.2-codexModèle indépendantOpenAI · Stable2026-01-14Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.0Valeur · Estimated54.5
Version comparison review8/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 59.8 (estimated) · 3/19 observed / reasoning 68.2 (estimated) · 3/13 observed / writing 58.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 4 benchmarksReference: gpt-5.2-chat-latest-20260210 · 4 benchmarksReference: gpt-5.4 · 1 benchmarksReview: below gpt-5.1-codex by 1.6 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · IndependentUsage entrée · par million de Tokens3 500 000 pointsLecture du cache · par million de Tokens350 000 pointsUsage sortie · par million de Tokens28 000 000 points
qwen-MiniMax/MiniMax-M2.1
Vérification en attente (UTC+8)
qwen-minimax-minimax-m2.1Modèle indépendantMiniMax · Stable2025-12-23Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens575 342 pointsLecture du cache · par million de Tokens57 534 pointsUsage sortie · par million de Tokens2 301 370 points
GLM-4.7
Vérification en attente (UTC+8)
glm-4.7Modèle indépendantZhipu · Stable2025-12-22Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated60.2Valeur · Estimated60.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.3 (estimated) · 2/19 observed / reasoning 63.5 (estimated) · 1/13 observed / writing 53.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 31 999 Token · Output 0 – 199 TokenUsage entrée · par million de Tokens547 945 pointsLecture du cache · par million de Tokens109 589 pointsUsage sortie · par million de Tokens2 191 781 points
Input 0 – 31 999 Token · Output 200+ TokenUsage entrée · par million de Tokens821 918 pointsLecture du cache · par million de Tokens164 384 pointsUsage sortie · par million de Tokens3 835 616 points
Input 32 000+ TokenUsage entrée · par million de Tokens1 095 890 pointsLecture du cache · par million de Tokens219 178 pointsUsage sortie · par million de Tokens4 383 562 points
GPT Image 1.5
Vérification en attente (UTC+8)
gpt-image-1.5Modèle indépendantOpenAI · Stable2025-12-16Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance76.0Valeur53.2
Usage entrée · par million de Tokens10 000 000 pointsLecture du cache · par million de Tokens2 500 000 pointsUsage entrée · Image · par million de Tokens16 000 000 pointsLecture du cache · Image · par million de Tokens4 000 000 pointsUsage sortie · par million de Tokens20 000 000 pointsUsage sortie · Image · par million de Tokens64 000 000 points
Wan2.6-I2V
Vérification en attente (UTC+8)
wan2.6-i2vModèle indépendantAlibaba Cloud · Stable2025-12-16Dernière vérification du prixVérification en attente (UTC+8)
Performance53.2Valeur45.3
Version comparison reviewProvisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%Review: below wan2.5-i2v-preview by 2.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · IndependentGénération vidéo 720P · par seconde164 384 pointsGénération vidéo 1080P · par seconde273 973 points
Wan2.6-Image
Vérification en attente (UTC+8)
wan2.6-imageModèle indépendantAlibaba Cloud · Stable2025-12-16Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance31.6Valeur39.2
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentUsage sortie · Image · par image54 795 points
qwen-Wan2.6-R2V
wan2.6-r2vModèle indépendantWan · Stable2025-12-16Pas de prix fixe ; facturation selon le servicePerformance · Estimated55.3Valeur · Estimated53.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Wan2.6-T2I
Vérification en attente (UTC+8)
wan2.6-t2iModèle indépendantAlibaba Cloud · Stable2025-12-16Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance50.0Valeur52.1
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentUsage sortie · Image · par image54 795 points
Wan2.6-T2V
Vérification en attente (UTC+8)
wan2.6-t2vModèle indépendantAlibaba Cloud · Stable2025-12-16Dernière vérification du prixVérification en attente (UTC+8)
Performance57.4Valeur48.3
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGénération vidéo 720P · par seconde164 384 pointsGénération vidéo 1080P · par seconde273 973 points
Cohere Rerank v4.0 Pro
Vérification en attente (UTC+8)
cohere-rerank-v4.0-proModèle indépendantCohere · Stable2025-12-11Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated65.8Valeur · Estimated61.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-0.6B · 68.8Reference: gte-multilingual-reranker-base · 62.7Reference: BGE-reranker-v2-m3 · 57.7qwen-rerank-public · OfficialReclassement · par 1 000 unités de recherche5 000 000 points
GPT-5.2
Vérification en attente (UTC+8)
gpt-5.2Modèle indépendantOpenAI · Stable2025-12-11Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated61.7Valeur · Estimated54.3
Version comparison review12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 52.5 (estimated) · 4/19 observed / reasoning 73.8 (estimated) · 4/13 observed / writing 58.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.4 · 1 benchmarksReview: below gpt-5.1 by 2.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentUsage entrée · par million de Tokens3 500 000 pointsLecture du cache · par million de Tokens350 000 pointsUsage sortie · par million de Tokens28 000 000 points
GPT-5.1 Codex Max
Vérification en attente (UTC+8)
gpt-5.1-codex-maxModèle indépendantOpenAI · Stable2025-12-04Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated72.5Valeur · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 69.3 (estimated) · 0/19 observed / reasoning 78.4 (estimated) · 0/13 observed / writing 69.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-6-sol-max · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.4 · 1 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 500 000 pointsLecture du cache · par million de Tokens250 000 pointsUsage sortie · par million de Tokens20 000 000 points
Mistral Large 3
Vérification en attente (UTC+8)
mistral-large-3Modèle indépendantMistral AI · Stable2025-12-02Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated60.6Valeur · Estimated60.8
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.7 (estimated) · 2/19 observed / reasoning 66.7 (estimated) · 1/13 observed / writing 60.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 000 000 pointsUsage sortie · par million de Tokens3 000 000 points
qwen-ViduQ2-Pro-fast_img2video
qwen-vidu-viduq2-pro-fast_img2videoModèle indépendantvidu · Stable2025-12-02Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3-LiveTranslate-Flash
qwen3-livetranslate-flashModèle indépendantQwen · Stable2025-12-01Pas de prix fixe ; facturation selon le servicePerformance · Estimated58.2Valeur · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3-Omni-Flash
qwen3-omni-flashModèle indépendantQwen · Stable2025-12-01Pas de prix fixe ; facturation selon le servicePerformance · Estimated58.2Valeur · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-SiliconFlow DeepSeek-V3.2
qwen-siliconflow-deepseek-v3.2Modèle indépendantDeepSeek · Stable2025-12-01Pas de prix fixe ; facturation selon le servicePerformance · Estimated45.8Valeur · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.1 (estimated) · 0/19 observed / reasoning 54.2 (estimated) · 0/13 observed / writing 45.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.2-exp · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Vanchin/DeepSeek-V3.2-think
qwen-vanchin-deepseek-v3.2-thinkModèle indépendantDeepSeek · Stable2025-12-01Pas de prix fixe ; facturation selon le servicePerformance · Estimated45.8Valeur · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.1 (estimated) · 0/19 observed / reasoning 54.2 (estimated) · 0/13 observed / writing 45.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.2-exp · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3-TTS-Flash-Realtime
qwen3-tts-flash-realtimeModèle indépendantQwen · Stable2025-11-27Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Z-Image-Turbo
Vérification en attente (UTC+8)
z-image-turboModèle indépendantAlibaba Cloud · Stable2025-11-26Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance28.8Valeur50.2
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentUsage sortie · Image · par image27 398 points
FLUX.2 [flex]
Vérification en attente (UTC+8)
flux.2-flexModèle indépendantBlack Forest Labs · Stable2025-11-25Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance46.8Valeur32.8
Usage entrée · Image · par mégapixel100 000 pointsUsage sortie · Image · par mégapixel100 000 points
FLUX.2 Pro
Vérification en attente (UTC+8)
flux.2-proModèle indépendantBlack Forest Labs · Stable2025-11-25Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance49.9Valeur64.9
Premier mégapixel · par mégapixel60 000 pointsMégapixel suivant · par mégapixel30 000 points
claude-opus-4-5
claude-opus-4-5Modèle indépendantAnthropic · Stable2025-11-24Pas de prix fixe ; facturation selon le servicePerformance · Estimated67.9Valeur—
Shared exact-model performance from claude-opus-4-5; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.9 (estimated) · 0/19 observed / reasoning 71.8 (estimated) · 0/13 observed / writing 67.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-opus-4-6 · 7 benchmarksReference: claude-opus-4-5-20251101 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
claude-opus-4-5-100
claude-opus-4-5-100Modèle indépendantAnthropic · Stable2025-11-24Pas de prix fixe ; facturation selon le servicePerformance · Estimated67.9Valeur—
Shared exact-model performance from claude-opus-4-5; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.9 (estimated) · 0/19 observed / reasoning 71.8 (estimated) · 0/13 observed / writing 67.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-opus-4-6 · 7 benchmarksReference: claude-opus-4-5-20251101 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Grok 4.1 Fast Non-Reasoning
Vérification en attente (UTC+8)
grok-4-1-fast-non-reasoningModèle indépendantxAI · Stable2025-11-19Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated62.1
Shared exact-model performance from grok-4-1-fast-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens400 000 pointsLecture du cache · par million de Tokens100 000 pointsUsage sortie · par million de Tokens1 000 000 points
Grok 4.1 Fast Reasoning
Vérification en attente (UTC+8)
grok-4-1-fast-reasoningModèle indépendantxAI · Stable2025-11-19Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated59.5Valeur · Estimated64.1
Shared exact-model performance from grok-4-1-fast-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.3 (estimated) · 2/19 observed / reasoning 65.8 (estimated) · 1/13 observed / writing 59.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentUsage entrée · par million de Tokens400 000 pointsLecture du cache · par million de Tokens100 000 pointsUsage sortie · par million de Tokens1 000 000 points
Gemini 3 Pro Preview-100
gemini-3-pro-previewModèle indépendantGoogle · Stable2025-11-18Pas de prix fixe ; facturation selon le servicePerformance · Estimated69.4Valeur · Estimated63.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 48.1 (estimated) · 0/19 observed / reasoning 77.5 (estimated) · 0/13 observed / writing 82.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.1-pro-preview-high · 7 benchmarksReference: gemini-3-pro · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Veo 3.1 Fast Generate 001-100
veo-3.1-fast-generate-001Modèle indépendantGoogle · Stable2025-11-17Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Veo 3.1 Generate 001-100
veo-3.1-generate-001Modèle indépendantGoogle · Stable2025-11-17Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT-5.1
Vérification en attente (UTC+8)
gpt-5.1Modèle indépendantOpenAI · Stable2025-11-13Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated63.8Valeur · Estimated57.2
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.9 (estimated) · 2/19 observed / reasoning 73.2 (estimated) · 1/13 observed / writing 63.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 500 000 pointsLecture du cache · par million de Tokens250 000 pointsUsage sortie · par million de Tokens20 000 000 points
GPT-5.1 Codex
Vérification en attente (UTC+8)
gpt-5.1-codexModèle indépendantOpenAI · Stable2025-11-13Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated63.6Valeur · Estimated57.1
1/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.2 (estimated) · 1/19 observed / reasoning 70.3 (estimated) · 0/13 observed / writing 62.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.1 · 4 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 500 000 pointsLecture du cache · par million de Tokens250 000 pointsUsage sortie · par million de Tokens20 000 000 points
GPT-5.1 Codex Mini
Vérification en attente (UTC+8)
gpt-5.1-codex-miniModèle indépendantOpenAI · Stable2025-11-13Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated43.1Valeur · Estimated49.4
1/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.6 (estimated) · 1/19 observed / reasoning 48.9 (estimated) · 0/13 observed / writing 40.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4-mini · 7 benchmarksReference: gpt-5-mini · 4 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens500 000 pointsLecture du cache · par million de Tokens50 000 pointsUsage sortie · par million de Tokens4 000 000 points
Lyria 002-100
lyria-002Modèle indépendantGoogle · Stable2025-10-27Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ2_reference2video
qwen-vidu-viduq2_reference2videoModèle indépendantvidu · Stable2025-10-21Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ2_text2video
qwen-vidu-viduq2_text2videoModèle indépendantvidu · Stable2025-10-21Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Vanchin/DeepSeek-OCR
qwen-vanchin-deepseek-ocrModèle indépendantDeepSeek · Stable2025-10-20Pas de prix fixe ; facturation selon le servicePerformance · Estimated81.8Valeur · Estimated72.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
claude-haiku-4-5
claude-haiku-4-5Modèle indépendantAnthropic · Stable2025-10-15Pas de prix fixe ; facturation selon le servicePerformance · Estimated60.4Valeur · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.5 (estimated) · 0/19 observed / reasoning 63.8 (estimated) · 0/13 observed / writing 60.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-haiku-4-5-20251001 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
claude-haiku-4-5-100
claude-haiku-4-5-100Modèle indépendantAnthropic · Stable2025-10-15Pas de prix fixe ; facturation selon le servicePerformance · Estimated60.4Valeur · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.5 (estimated) · 0/19 observed / reasoning 63.8 (estimated) · 0/13 observed / writing 60.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-haiku-4-5-20251001 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT-5 Pro
Vérification en attente (UTC+8)
gpt-5-proModèle indépendantOpenAI · Stable2025-10-06Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.5Valeur · Estimated41.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.9 (estimated) · 0/19 observed / reasoning 61.9 (estimated) · 0/13 observed / writing 51.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5 · 5 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens20 000 000 pointsUsage sortie · par million de Tokens240 000 000 points
GPT Audio Mini
Vérification en attente (UTC+8)
gpt-audio-miniModèle indépendantOpenAI · Stable2025-10-06Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated52.6Valeur · Estimated66.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · OfficialUsage entrée · par million de Tokens1 200 000 pointsUsage sortie · par million de Tokens4 800 000 pointsUsage entrée · Audio · par million de Tokens20 000 000 pointsUsage sortie · Audio · par million de Tokens40 000 000 points
GPT Image 1 Mini
Vérification en attente (UTC+8)
gpt-image-1-miniModèle indépendantOpenAI · Stable2025-10-06Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance20.1Valeur44.1
Usage entrée · par million de Tokens4 000 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage entrée · Image · par million de Tokens5 000 000 pointsLecture du cache · Image · par million de Tokens500 000 pointsUsage sortie · Image · par million de Tokens16 000 000 points
GPT Realtime Mini
Vérification en attente (UTC+8)
gpt-realtime-miniModèle indépendantOpenAI · Stable2025-10-06Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated54.0Valeur · Estimated67.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-realtime-2025-08-28 · 59.9Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · OfficialUsage entrée · par million de Tokens1 200 000 pointsLecture du cache · par million de Tokens120 000 pointsUsage sortie · par million de Tokens4 800 000 pointsUsage entrée · Image · par million de Tokens1 600 000 pointsLecture du cache · Image · par million de Tokens160 000 pointsUsage entrée · Audio · par million de Tokens20 000 000 pointsLecture du cache · Audio · par million de Tokens600 000 pointsUsage sortie · Audio · par million de Tokens40 000 000 points
Gemini 2.5 Flash TTS-100
gemini-2.5-flash-ttsModèle indépendantGoogle · Stable2025-09-30Pas de prix fixe ; facturation selon le servicePerformance · Estimated87.1Valeur · Estimated76.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Gemini-flash · 87.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Gemini 2.5 Pro TTS-100
gemini-2.5-pro-ttsModèle indépendantGoogle · Stable2025-09-30Pas de prix fixe ; facturation selon le servicePerformance · Estimated82.6Valeur · Estimated72.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sora 2
Vérification en attente (UTC+8)
sora-2Modèle indépendantOpenAI · Aperçu2025-09-30Dernière vérification du prixVérification en attente (UTC+8)
Performance66.0Valeur50.4
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGénération vidéo · par seconde200 000 points
claude-sonnet-4-5
claude-sonnet-4-5Modèle indépendantAnthropic · Stable2025-09-29Pas de prix fixe ; facturation selon le servicePerformance · Estimated61.6Valeur · Estimated58.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.8 (estimated) · 0/19 observed / reasoning 66.2 (estimated) · 0/13 observed / writing 59.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-sonnet-4-6 · 7 benchmarksReference: claude-sonnet-4-5-20250929 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ2-Pro_img2video
qwen-vidu-viduq2-pro_img2videoModèle indépendantvidu · Stable2025-09-24Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ2-Pro_start-end2video
qwen-vidu-viduq2-pro_start-end2videoModèle indépendantvidu · Stable2025-09-24Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ2-Turbo_img2video
qwen-vidu-viduq2-turbo_img2videoModèle indépendantvidu · Stable2025-09-24Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ2-Turbo_start-end2video
qwen-vidu-viduq2-turbo_start-end2videoModèle indépendantvidu · Stable2025-09-24Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT-5 Codex
Vérification en attente (UTC+8)
gpt-5-codexModèle indépendantOpenAI · Stable2025-09-23Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated59.1Valeur · Estimated53.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 59.5 (estimated) · 0/19 observed / reasoning 63.0 (estimated) · 0/13 observed / writing 54.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5 · 5 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 500 000 pointsLecture du cache · par million de Tokens250 000 pointsUsage sortie · par million de Tokens20 000 000 points
qwen-SiliconFlow DeepSeek-V3.1-Terminus
qwen-siliconflow-deepseek-v3.1-terminusModèle indépendantDeepSeek · Stable2025-09-22Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.9Valeur · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Vanchin/DeepSeek-V3.1-Terminus
qwen-vanchin-deepseek-v3.1-terminusModèle indépendantDeepSeek · Stable2025-09-22Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.9Valeur · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3-TTS-Flash
Vérification en attente (UTC+8)
qwen3-tts-flashModèle indépendantAlibaba Cloud · Stable2025-09 (mois officiel uniquement)Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated74.4Valeur · Estimated82.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · OfficialAudio · pour 10 000 caractères219 179 points
Chirp 3-100
chirp-3Modèle indépendantGoogle · Stable2025-08-29Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT Realtime
Vérification en attente (UTC+8)
gpt-realtimeModèle indépendantOpenAI · Stable2025-08-28Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated59.9Valeur · Estimated41.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · OfficialUsage entrée · par million de Tokens8 000 000 pointsLecture du cache · par million de Tokens800 000 pointsUsage sortie · par million de Tokens32 000 000 pointsUsage entrée · Image · par million de Tokens10 000 000 pointsLecture du cache · Image · par million de Tokens1 000 000 pointsUsage entrée · Audio · par million de Tokens64 000 000 pointsLecture du cache · Audio · par million de Tokens800 000 pointsUsage sortie · Audio · par million de Tokens128 000 000 points
GPT-5
Vérification en attente (UTC+8)
gpt-5Modèle indépendantOpenAI · Stable2025-08-07Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated58.7Valeur · Estimated53.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.6 (estimated) · 2/19 observed / reasoning 65.6 (estimated) · 1/13 observed / writing 56.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 500 000 pointsLecture du cache · par million de Tokens250 000 pointsUsage sortie · par million de Tokens20 000 000 points
GPT-5 Mini
Vérification en attente (UTC+8)
gpt-5-miniModèle indépendantOpenAI · Stable2025-08-07Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated43.1Valeur · Estimated49.4
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.6 (estimated) · 1/19 observed / reasoning 48.9 (estimated) · 1/13 observed / writing 40.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4-mini · 7 benchmarksReference: gpt-5.1-codex-mini · 1 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens500 000 pointsLecture du cache · par million de Tokens50 000 pointsUsage sortie · par million de Tokens4 000 000 points
GPT-5 Nano
Vérification en attente (UTC+8)
gpt-5-nanoModèle indépendantOpenAI · Stable2025-08-07Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated44.4Valeur · Estimated57.0
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 43.4 (estimated) · 1/19 observed / reasoning 50.3 (estimated) · 1/13 observed / writing 39.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-nano-2025-04-14 · 7 benchmarksReference: gpt-5.4-nano · 7 benchmarksReference: gpt-5 · 1 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens100 000 pointsLecture du cache · par million de Tokens10 000 pointsUsage sortie · par million de Tokens800 000 points
GPT-OSS 120B-100
openai-gpt-oss-120b-maas-001Modèle indépendantOpenAI · Stable2025-08-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated57.3Valeur · Estimated55.1
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.4 (estimated) · 1/19 observed / reasoning 63.0 (estimated) · 1/13 observed / writing 51.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3-Coder-Flash
Vérification en attente (UTC+8)
qwen3-coder-flashModèle indépendantQwen · Stable2025-08-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated58.2Valeur · Estimated64.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32 000 TokenUsage entrée · par million de Tokens273 973 pointsLecture du cache · par million de Tokens54 795 pointsUsage sortie · par million de Tokens1 095 890 points
Input 32 001 – 128 000 TokenUsage entrée · par million de Tokens410 959 pointsLecture du cache · par million de Tokens82 192 pointsUsage sortie · par million de Tokens1 643 836 points
Input 128 001 – 256 000 TokenUsage entrée · par million de Tokens684 932 pointsLecture du cache · par million de Tokens136 986 pointsUsage sortie · par million de Tokens2 739 726 points
Input 256 001+ TokenUsage entrée · par million de Tokens1 369 863 pointsLecture du cache · par million de Tokens273 973 pointsUsage sortie · par million de Tokens6 849 315 points
Qwen-Flash
Vérification en attente (UTC+8)
qwen-flashModèle indépendantQwen · Stable2025-08-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated59.4Valeur · Estimated70.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.4 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 128 000 TokenUsage entrée · par million de Tokens41 096 pointsLecture du cache · par million de Tokens8 219 pointsUsage sortie · par million de Tokens410 959 points
Input 128 001 – 256 000 TokenUsage entrée · par million de Tokens164 384 pointsLecture du cache · par million de Tokens32 877 pointsUsage sortie · par million de Tokens1 643 836 points
Input 256 001+ TokenUsage entrée · par million de Tokens328 767 pointsLecture du cache · par million de Tokens65 753 pointsUsage sortie · par million de Tokens3 287 671 points
doubao-glm-4-5-air
doubao-glm-4-5-air-20250728Instantané / version fixe · Accès uniqueZhipu AI · Stable2025-07-28Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GLM-4.5-Air
Vérification en attente (UTC+8)
glm-4.5-airModèle indépendantZhipu · Stable2025-07-27Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated59.3Valeur · Estimated64.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.9 (estimated) · 0/19 observed / reasoning 64.2 (estimated) · 0/13 observed / writing 55.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-4.5-air · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 31 999 Token · Output 0 – 199 TokenUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens43 836 pointsUsage sortie · par million de Tokens547 945 points
Input 0 – 31 999 Token · Output 200+ TokenUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens43 836 pointsUsage sortie · par million de Tokens1 643 836 points
Input 32 000+ TokenUsage entrée · par million de Tokens328 767 pointsLecture du cache · par million de Tokens65 753 pointsUsage sortie · par million de Tokens2 191 781 points
qwen-pixverse/pixverse-lipsync
qwen-pixverse-pixverse-lipsyncModèle indépendantpixverse · Stable2025-07-14Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Plus
Vérification en attente (UTC+8)
qwen-plusModèle indépendantQwen · Stable2025-06-24Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated44.2Valeur · Estimated55.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.6 (estimated) · 0/19 observed / reasoning 46.7 (estimated) · 0/13 observed / writing 40.3 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 128 000 TokenUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens43 836 pointsUsage sortie · par million de Tokens547 945 points
Input 128 001 – 256 000 TokenUsage entrée · par million de Tokens657 534 pointsLecture du cache · par million de Tokens131 507 pointsUsage sortie · par million de Tokens5 479 452 points
Input 256 001+ TokenUsage entrée · par million de Tokens1 315 068 pointsLecture du cache · par million de Tokens263 014 pointsUsage sortie · par million de Tokens13 150 685 points
qwen-SiliconFlow DeepSeek-R1-0528
qwen-siliconflow-deepseek-r1-0528Modèle indépendantDeepSeek · Stable2025-05-28Pas de prix fixe ; facturation selon le servicePerformance · Estimated43.2Valeur · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Mistral OCR 2505-100
mistralai-mistral-ocr-2505-001Modèle indépendantMistral AI · Stable2025-05-22Pas de prix fixe ; facturation selon le servicePerformance · Estimated81.8Valeur · Estimated72.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
mistral-medium-2505
mistral-medium-2505Modèle indépendantMistral AI · Stable2025-05-07Pas de prix fixe ; facturation selon le servicePerformance · Estimated54.1Valeur · Estimated52.9
Version comparison review4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.4 (estimated) · 1/19 observed / reasoning 59.7 (estimated) · 1/13 observed / writing 55.3 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below mistral-medium-3-5 by 6.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Phi-4 Reasoning
Vérification en attente (UTC+8)
phi-4-reasoningModèle indépendantMicrosoft · Stable2025-04-30Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens250 000 pointsUsage sortie · par million de Tokens1 000 000 points
o3
Vérification en attente (UTC+8)
o3Modèle indépendantOpenAI · Stable2025-04-16Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.8Valeur · Estimated56.1
7/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 18%coding 57.9 (estimated) · 1/19 observed / reasoning 70.4 (estimated) · 4/13 observed / writing 60.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: o3-2025-04-16 · 4 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksReference: DeepSeek V4 Pro (High) (0813) · 1 benchmarksopenai-simple-evals · Officialmicrosoft-mai-report · Officialmistral-codestral · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens4 000 000 pointsLecture du cache · par million de Tokens1 000 000 pointsUsage sortie · par million de Tokens16 000 000 points
Veo 2.0 Generate 001-100
veo-2.0-generate-001Modèle indépendantGoogle · Stable2025-04-09Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Llama 4 Maverick 17B 128E
Vérification en attente (UTC+8)
llama-4-maverick-17b-128e-instruct-fp8Modèle indépendantMeta · Stable2025-04-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated60.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens500 000 pointsUsage sortie · par million de Tokens2 000 000 points
Llama 4 Maverick 17B 128E-100
llama-4-maverick-17b-128e-instruct-maas-100Modèle indépendantMeta · Stable2025-04-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Llama 4 Scout 17B 16E Instruct-100
meta-llama-4-scout-17b-16e-instruct-maas-001Modèle indépendantMeta · Stable2025-04-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated53.1Valeur · Estimated52.2
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.1 (estimated) · 1/19 observed / reasoning 56.7 (estimated) · 1/13 observed / writing 47.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-SiliconFlow DeepSeek-V3-0324
qwen-siliconflow-deepseek-v3-0324Modèle indépendantDeepSeek · Stable2025-03-24Pas de prix fixe ; facturation selon le servicePerformance · Estimated39.9Valeur · Estimated42.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.0 (estimated) · 0/19 observed / reasoning 48.3 (estimated) · 0/13 observed / writing 35.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-coder-480b-a35b-instruct · 5 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below qwen-deepseek-r1-0528 by 4.6 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
GPT-4o Mini Transcribe
Vérification en attente (UTC+8)
gpt-4o-mini-transcribeModèle indépendantOpenAI · Stable2025-03-20Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.4Valeur · Estimated94.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentUsage entrée · Audio · par million de Tokens6 000 000 pointsUsage entrée · par million de Tokens2 500 000 pointsUsage sortie · par million de Tokens10 000 000 points
GPT-4o Mini TTS
Vérification en attente (UTC+8)
gpt-4o-mini-ttsModèle indépendantOpenAI · Stable2025-03-20Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated59.8Valeur · Estimated56.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: GPT-4o-mini-tts · 59.8qwen-tts-public · OfficialUsage entrée · par million de Tokens1 200 000 pointsUsage sortie · Audio · par million de Tokens24 000 000 points
GPT-4o Transcribe
Vérification en attente (UTC+8)
gpt-4o-transcribeModèle indépendantOpenAI · Stable2025-03-20Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance91.4Valeur64.0
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 18%qwen-asr-report · IndependentUsage entrée · Audio · par million de Tokens12 000 000 pointsUsage entrée · par million de Tokens5 000 000 pointsUsage sortie · par million de Tokens20 000 000 points
mistral-small-2503
mistral-small-2503Modèle indépendantMistral AI · Stable2025-03-17Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.0Valeur—
Shared exact-model performance from mistral-small-2503; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.7 (estimated) · 0/19 observed / reasoning 59.2 (estimated) · 0/13 observed / writing 52.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: mistral-small-2506 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Mistral Small 3.1-100
Vérification en attente (UTC+8)
mistral-small-2503-100Modèle indépendantGoogle · Aperçu2025-03-17Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.0Valeur · Estimated64.3
Shared exact-model performance from mistral-small-2503; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.7 (estimated) · 0/19 observed / reasoning 59.2 (estimated) · 0/13 observed / writing 52.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: mistral-small-2506 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens200 000 pointsUsage sortie · par million de Tokens600 000 points
Text Embedding Large Exp 03 07-100
text-embedding-large-exp-03-07Modèle indépendantGoogle · Stable2025-03-07Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-DeepSeek-R1-Distill-Qwen-1.5B
qwen-deepseek-r1-distill-qwen-1.5bModèle indépendantDeepSeek · Stable2025-01-20Pas de prix fixe ; facturation selon le servicePerformance · Estimated43.2Valeur · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Codestral 2501
Vérification en attente (UTC+8)
codestral-2501Modèle indépendantMistral AI · Stable2025-01-13Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated60.1
9/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 18%coding 56.8 (estimated) · 9/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksReference: smaug-flash · 3 benchmarksmistral-codestral · Officialmicrosoft-mai-report · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens600 000 pointsUsage sortie · par million de Tokens1 800 000 points
Ministral-3B
ministral-3bModèle indépendantMistral AI · Stable2024-10-16Pas de prix fixe ; facturation selon le servicePerformance · Estimated49.2Valeur · Estimated49.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.8 (estimated) · 0/19 observed / reasoning 50.7 (estimated) · 0/13 observed / writing 43.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: ministral-8b-2410 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Long
Vérification en attente (UTC+8)
qwen-longModèle indépendantQwen · Stable2024-05-20Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated52.5Valeur · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 48.7 (estimated) · 0/19 observed / reasoning 58.7 (estimated) · 0/13 observed / writing 50.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: qwen-glm-4.5 · 4 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens136 986 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens547 945 points
Text Embedding 3 Large
Vérification en attente (UTC+8)
text-embedding-3-largeModèle indépendantOpenAI · Stable2024-01-25Dernière vérification du prixVérification en attente (UTC+8)
Performance64.6Valeur45.2
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · OfficialEntrée vectorielle · par million de Tokens260 000 points
Text Embedding 3 Small
Vérification en attente (UTC+8)
text-embedding-3-smallModèle indépendantOpenAI · Stable2024-01-25Dernière vérification du prixVérification en attente (UTC+8)
Performance62.3Valeur71.3
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · OfficialEntrée vectorielle · par million de Tokens40 000 points
Cohere-embed-v3-english
cohere-embed-v3-englishModèle indépendantCohere · Stable2023-11-02Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Cohere-embed-v3-multilingual
cohere-embed-v3-multilingualModèle indépendantCohere · Stable2023-11-02Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Text Embedding Ada 002
Vérification en attente (UTC+8)
text-embedding-ada-002Modèle indépendantOpenAI · Stable2022-12-15Dernière vérification du prixVérification en attente (UTC+8)
Performance61.0Valeur46.6
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · OfficialEntrée vectorielle · par million de Tokens200 000 points
Qwen-Image-2.1-Turbo
qwen-image-2.1-turboModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-14Pas de prix fixe ; facturation selon le servicePerformance—Valeur—
Non évaluéTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Chirp 2-100
chirp-2-001Modèle indépendantGoogle · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
语音生成CosyVoice-v3.5-flash大模型
cosyvoice-v3.5-flashModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated75.4Valeur · Estimated67.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
语音生成CosyVoice-v3.5-plus大模型
cosyvoice-v3.5-plusModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated75.4Valeur · Estimated67.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
doubao-GLM-5.3-Flash
Vérification en attente (UTC+8)
doubao-glm-5-3-flash-260828Instantané / version fixe · Accès uniqueZhipu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 56.6microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens63 014 pointsUsage sortie · par million de Tokens767 123 points
qwen2-5-72b
doubao-qwen2-5-72b-20240919Instantané / version fixe · Accès uniqueQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen3-0-6b
doubao-qwen3-0-6b-20250429Instantané / version fixe · Accès uniqueQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen3-14b
doubao-qwen3-14b-20250429Instantané / version fixe · Accès uniqueQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen3-32b
doubao-qwen3-32b-20250429Instantané / version fixe · Accès uniqueQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen3-8b
doubao-qwen3-8b-20250429Instantané / version fixe · Accès uniqueQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
doubao-seed-translation
doubao-seed-translation-250915Instantané / version fixe · Accès uniqueDoubao · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
doubao-smart-router
doubao-smart-router-250928Instantané / version fixe · Accès uniqueDoubao · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated50.0Valeur · Estimated50.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: o1-mini · 50.0Reference: qwen3.6-plus · 50.2Reference: gemini-2.0-flash-001 · 50.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
FaceChain人物图像检测
facechain-facedetectModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.5Valeur · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Fun-ASR语音识别
fun-asrModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Fun-ASR实时语音识别
fun-asr-realtimeModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
音乐生成 Preview
fun-music-previewModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
音乐生成
fun-music-v1Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Grok 4.20 Non-Reasoning-100
Vérification en attente (UTC+8)
grok-4-20-non-reasoning-100Modèle indépendantxAI · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur—
Shared exact-model performance from grok-4-20-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens2 500 000 pointsLecture du cache · par million de Tokens400 000 pointsUsage sortie · par million de Tokens5 000 000 points
Grok 4.20 Reasoning-100
grok-4-20-reasoning-100Modèle indépendantxAI · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur—
Shared exact-model performance from grok-4-20-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Grok 4.3-100
grok-4.3-100Modèle indépendantxAI · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.8Valeur—
Shared exact-model performance from grok-4.3; coverage refers to public model benchmarks, not tests of every platform deployment.12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.8 (estimated) · 4/19 observed / reasoning 48.3 (estimated) · 4/13 observed / writing 47.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-HappyHorse-1.0-Video-Edit
happyhorse-1.0-video-editModèle indépendantHappyHorse · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated80.9Valeur · Estimated71.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
图像擦除补全
image-erase-completionModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.5Valeur · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
人物实例分割
image-instance-segmentationModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.5Valeur · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Codestral 2-100
mistralai-codestral-2-001Modèle indépendantMistral AI · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Mistral Medium 3-100
mistralai-mistral-medium-3-001Modèle indépendantMistral AI · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Paraformer语音识别-8k-v2
paraformer-8k-v2Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Paraformer实时语音识别-8k-v2
paraformer-realtime-8k-v2Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Paraformer实时语音识别-v2
paraformer-realtime-v2Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Paraformer语音识别-v2
paraformer-v2Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3-ASR-Flash-Filetrans
qwen3-asr-flash-filetransModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen3-ASR-Flash-Realtime
qwen3-asr-flash-realtimeModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.6Valeur · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Audio-3.1-ASR-Flash
qwen-audio-3.1-asr-flashModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Audio-3.1-ASR-Flash-Filetrans
qwen-audio-3.1-asr-flash-filetransModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Audio-3.1-ASR-Flash-Message
qwen-audio-3.1-asr-flash-messageModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Audio-3.1-ASR-Flash-Streaming
qwen-audio-3.1-asr-flash-streamingModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated91.4Valeur · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Audio-3.1-TTS-Flash
qwen-audio-3.1-tts-flashModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated74.4Valeur · Estimated67.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Audio-3.1-TTS-Next
qwen-audio-3.1-tts-nextModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated74.4Valeur · Estimated67.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Doc-Turbo
Vérification en attente (UTC+8)
qwen-doc-turboModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated48.7Valeur · Estimated49.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.8 (estimated) · 0/19 observed / reasoning 52.3 (estimated) · 0/13 observed / writing 47.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens164 384 pointsLecture du cache · par million de Tokens32 877 pointsUsage sortie · par million de Tokens273 973 points
Qwen-Flash-Character
Vérification en attente (UTC+8)
qwen-flash-characterModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated59.9Valeur · Estimated70.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.1 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens68 493 pointsLecture du cache · par million de Tokens13 699 pointsUsage sortie · par million de Tokens410 959 points
qwen-Kling Video 3.0 Turbo
qwen-kling-kling-v3-turbo-video-generationModèle indépendantkling · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-speech-02-hd
qwen-minimax-speech-02-hdModèle indépendantmini-max · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated32.9Valeur · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 32.7 (estimated) · 0/19 observed / reasoning 39.5 (estimated) · 0/13 observed / writing 26.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-speech-02-turbo
qwen-minimax-speech-02-turboModèle indépendantmini-max · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated34.1Valeur · Estimated38.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 39.8 (estimated) · 0/13 observed / writing 28.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-speech-2.8-hd
qwen-minimax-speech-2.8-hdModèle indépendantmini-max · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.1Valeur · Estimated45.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.0 (estimated) · 0/19 observed / reasoning 53.2 (estimated) · 0/13 observed / writing 41.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-instruct-2507 · 4 benchmarksReference: qwen3-235b-a22b-thinking-2507 · 4 benchmarksReference: qwen3-30b-a3b-instruct-2507 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-speech-2.8-turbo
qwen-minimax-speech-2.8-turboModèle indépendantmini-max · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated46.9Valeur · Estimated47.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 40.0 (estimated) · 0/19 observed / reasoning 56.2 (estimated) · 0/13 observed / writing 44.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen3-30b-a3b-instruct-2507 · 4 benchmarksReference: qwen3-max-2025-09-23 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-MT-Flash
qwen-mt-flashModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated59.4Valeur · Estimated56.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-MT-Image
qwen-mt-imageModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated34.1Valeur · Estimated38.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image · 20.0Reference: qwen-image-prompt-extend · 23.8Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-MT-Lite
qwen-mt-liteModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.3Valeur · Estimated54.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 0/19 observed / reasoning 60.6 (estimated) · 0/13 observed / writing 58.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: qwen3.8-max · 8 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-MT-Plus
qwen-mt-plusModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated46.7Valeur · Estimated47.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.9 (estimated) · 0/19 observed / reasoning 50.1 (estimated) · 0/13 observed / writing 43.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-PixVerse-V6-r2v
qwen-pixverse-pixverse-v6-r2vModèle indépendantpixverse · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Plus-Character
Vérification en attente (UTC+8)
qwen-plus-characterModèle indépendantqwen-domain-model · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated46.9Valeur · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.0 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 43.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens219 178 pointsLecture du cache · par million de Tokens43 836 pointsUsage sortie · par million de Tokens547 945 points
qwen-stepfun/step-5-preview
Vérification en attente (UTC+8)
qwen-stepfun-step-5-previewModèle indépendantStepFun · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated30.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens1 917 808 pointsLecture du cache · par million de Tokens95 890 pointsUsage sortie · par million de Tokens5 479 452 points
qwen-unisound/unisound-u2
qwen-unisound-unisound-u2Modèle indépendantunisound · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated32.9Valeur · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 32.7 (estimated) · 0/19 observed / reasoning 39.5 (estimated) · 0/13 observed / writing 26.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Vanchin/DeepSeek-R1
qwen-vanchin-deepseek-r1Modèle indépendantDeepSeek · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated43.2Valeur · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Vanchin/DeepSeek-V3
qwen-vanchin-deepseek-v3Modèle indépendantDeepSeek · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated42.6Valeur · Estimated44.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.2 (estimated) · 0/19 observed / reasoning 51.7 (estimated) · 0/13 observed / writing 39.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-no-thinking · 4 benchmarksReference: qwen3-next-80b-a3b-thinking · 4 benchmarksReference: qwen3-vl-235b-a22b-thinking · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below qwen-deepseek-r1-0528 by 1.9 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-vanchin/deepseek-v4-pro
qwen-vanchin-deepseek-v4-proModèle indépendantDeepSeek · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated71.1Valeur · Estimated64.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 67.0 (estimated) · 0/19 observed / reasoning 75.3 (estimated) · 0/13 observed / writing 70.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-max · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: qwen3.8-27b · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Vidu-image-lite_reference2image
qwen-vidu-vidu-image-lite_reference2imageModèle indépendantvidu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated66.4Valeur · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Vidu-image-pro_reference2image
qwen-vidu-vidu-image-pro_reference2imageModèle indépendantvidu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated66.4Valeur · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Vidu-image_reference2image
qwen-vidu-vidu-image_reference2imageModèle indépendantvidu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated73.8Valeur · Estimated66.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ2-fast_reference2image
qwen-vidu-viduq2-fast_reference2imageModèle indépendantvidu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated66.4Valeur · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ2-Pro_reference2image
qwen-vidu-viduq2-pro_reference2imageModèle indépendantvidu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated66.4Valeur · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-Ad_reference2video
qwen-vidu-viduq3-ad_reference2videoModèle indépendantvidu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-Drama_reference2video
qwen-vidu-viduq3-drama_reference2videoModèle indépendantvidu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-fast_reference2image
qwen-vidu-viduq3-fast_reference2imageModèle indépendantvidu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated85.0Valeur · Estimated74.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-3.0-pro · 85.0Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ViduQ3-Pro-fast_img2video
qwen-vidu-viduq3-pro-fast_img2videoModèle indépendantvidu · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Qwen-Voice-Enrollment
qwen-voice-enrollmentEntrée de service indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.7 (estimated) · 0/19 observed / reasoning 56.4 (estimated) · 0/13 observed / writing 50.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-ZHIPU/GLM-5.3-FlashX
Vérification en attente (UTC+8)
qwen-zhipu-glm-5.3-flashxModèle indépendantZhipu AI · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated41.0Valeur · Estimated37.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens547 945 pointsLecture du cache · par million de Tokens156 164 pointsUsage sortie · par million de Tokens1 917 808 points
Sambert语音合成-Beth
sambert-beth-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Betty
sambert-betty-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Brian
sambert-brian-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Cally
sambert-cally-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Camila
sambert-camila-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Cindy
sambert-cindy-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Clara
sambert-clara-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Donna
sambert-donna-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Eva
sambert-eva-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Hanna
sambert-hanna-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Indah
sambert-indah-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Perla
sambert-perla-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-Waan
sambert-waan-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知厨
sambert-zhichu-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知达
sambert-zhida-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知德
sambert-zhide-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知飞
sambert-zhifei-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知柜
sambert-zhigui-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.5Valeur · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知浩
sambert-zhihao-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知佳
sambert-zhijia-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知婧
sambert-zhijing-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知伦
sambert-zhilun-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知猫
sambert-zhimao-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知妙（多情感）
sambert-zhimiao-emo-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知茗
sambert-zhiming-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知墨
sambert-zhimo-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知楠
sambert-zhinan-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知娜
sambert-zhina-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知倩
sambert-zhiqian-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知琪
sambert-zhiqi-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知茹
sambert-zhiru-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知硕
sambert-zhishuo-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知树
sambert-zhishu-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知莎
sambert-zhistella-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知婷
sambert-zhiting-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知薇
sambert-zhiwei-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知祥
sambert-zhixiang-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知笑
sambert-zhixiao-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知雅
sambert-zhiya-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知晔
sambert-zhiye-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知颖
sambert-zhiying-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知媛
sambert-zhiyuan-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Sambert语音合成-知悦
sambert-zhiyue-v1Entrée de voix indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
鞋靴模特
shoemodel-v1Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.5Valeur · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
语音识别热词
speech-biasingEntrée de service indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
通用文本向量-async-v1
text-embedding-async-v1Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
通用文本向量-async-v2
text-embedding-async-v2Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
意图分类模型
tongyi-intent-detect-v3Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
伶鹊-对话分析-flash
Vérification en attente (UTC+8)
tongyi-xiaomi-analysis-flashModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens54 795 pointsLecture du cache · par million de Tokens10 959 pointsUsage sortie · par million de Tokens109 589 points
伶鹊-对话分析-pro
Vérification en attente (UTC+8)
tongyi-xiaomi-analysis-proModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens273 973 pointsLecture du cache · par million de Tokens54 795 pointsUsage sortie · par million de Tokens739 726 points
Translate LLM-100
translate-llmModèle indépendantGoogle · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
声动人像VideoRetalk
videoretalkModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
视频风格重绘
video-style-transformModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.0Valeur · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
虚拟模特V2
virtualmodel-v2Modèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated44.5Valeur · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
大模型声音复刻及声音设计
voice-enrollmentEntrée de service indépendanteQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated56.6Valeur · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.2-Animate-Mix
wan2.2-animate-mixModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.2-Animate-Move
wan2.2-animate-moveModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.2-KF2V-Flash
wan2.2-kf2v-flashModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-通义万相2.2-数字人-S2V
wan2.2-s2vModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.2-S2V-Detect
wan2.2-s2v-detectModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.2-T2I-Flash
wan2.2-t2i-flashModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.2-T2I-Plus
wan2.2-t2i-plusModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.5-I2I-Preview
wan2.5-i2i-previewModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated52.7Valeur · Estimated51.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.5-T2I-Preview
wan2.5-t2i-previewModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated51.5Valeur · Estimated51.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: wan2.5-i2v-preview · 55.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.6-R2V-Flash
wan2.6-r2v-flashModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated55.3Valeur · Estimated53.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.0-T2I-Turbo
wanx2.0-t2i-turboModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.1-ImageEdit
wanx2.1-imageeditModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.1-KF2V-Plus
wanx2.1-kf2v-plusModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.1-T2I-Plus
wanx2.1-t2i-plusModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.1-T2I-Turbo
wanx2.1-t2i-turboModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-Wan2.1-VACE-Plus
wanx2.1-vace-plusModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-创意海报生成
wanx-poster-generation-v1Modèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-万相-涂鸦作画
wanx-sketch-to-image-liteModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated34.8Valeur · Estimated39.4
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-人像风格重绘
wanx-style-repaint-v1Modèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-wanx-t2i
wanx-v1Modèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-虚拟模特
wanx-virtualmodelModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated36.9Valeur · Estimated40.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
qwen-万相-图像局部重绘
wanx-x-paintingModèle indépendantWan · StableAjout au catalogue (date de sortie à vérifier): 2026-10-05Pas de prix fixe ; facturation selon le servicePerformance · Estimated37.0Valeur · Estimated40.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
语音生成cosyvoice-v2大模型
Vérification en attente (UTC+8)
cosyvoice-v2Modèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated75.4Valeur · Estimated52.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · OfficialAudio · pour 10 000 caractères547 946 points
语音生成CosyVoice-v3-flash大模型
Vérification en attente (UTC+8)
cosyvoice-v3-flashModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated75.4Valeur · Estimated75.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · OfficialAudio · pour 10 000 caractères273 973 points
语音生成CosyVoice-v3-plus大模型
Vérification en attente (UTC+8)
cosyvoice-v3-plusModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated75.4Valeur · Estimated52.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · OfficialAudio · pour 10 000 caractères547 946 points
GUI-Plus
Vérification en attente (UTC+8)
gui-plusModèle indépendantQwen · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated56.6Valeur · Estimated61.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentUsage entrée · par million de Tokens410 959 pointsLecture du cache · par million de Tokens0 pointsUsage sortie · par million de Tokens1 232 877 points
通用多模态向量
Vérification en attente (UTC+8)
multimodal-embedding-v1Modèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.3Valeur · Estimated48.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEntrée vectorielle · par million de Tokens191 781 pointsUsage entrée · Image · par million de Tokens246 576 pointsEntrée vidéo · par million de Tokens246 576 points
Qwen2.5-VL-Embedding
Vérification en attente (UTC+8)
qwen2.5-vl-embeddingModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.3Valeur · Estimated48.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEntrée vectorielle · par million de Tokens191 781 pointsUsage entrée · Image · par million de Tokens493 151 points
Qwen3-ASR-Flash
Vérification en attente (UTC+8)
qwen3-asr-flashModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.4Valeur · Estimated94.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · par seconde61 points
千问3-Rerank
Vérification en attente (UTC+8)
qwen3-rerankModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated72.5Valeur · Estimated80.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · OfficialUsage entrée · par million de Tokens136 987 points
Qwen3-VL-Embedding
Vérification en attente (UTC+8)
qwen3-vl-embeddingModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.3Valeur · Estimated48.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEntrée vectorielle · par million de Tokens191 781 pointsUsage entrée · Image · par million de Tokens493 151 points
Qwen3-VL-Rerank
Vérification en attente (UTC+8)
qwen3-vl-rerankModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated72.5Valeur · Estimated80.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · OfficialUsage entrée · par million de Tokens136 987 pointsEntrée vidéo · par million de Tokens493 154 points
Tarif de responsabilité estimatif pour l’entrée vidéo, confirmé par le client. Le fournisseur n’a publié ni tarif vidéo officiel ni conversion des images en Token. Utilisé uniquement pour le catalogue et la réservation des tests ; il ne constitue pas un coût fournisseur et ne modifie pas les factures historiques.
Qwen-Image-2.0-Pro
Vérification en attente (UTC+8)
qwen-image-2.0-proModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated66.4Valeur · Estimated46.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4arena · Independentarena · IndependentUsage sortie · Image · par image136 987 points
Qwen-Image-3.0-Pro
Vérification en attente (UTC+8)
qwen-image-3.0-proModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance85.0Valeur59.5
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentImage Usage entrée 1K · par image5 480 pointsImage Usage entrée 2K · par image5 480 pointsImage Usage sortie 1K · par image68 494 pointsImage Usage sortie 2K · par image136 987 points
QwenVL-OCR
Vérification en attente (UTC+8)
qwen-vl-ocrModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated81.8Valeur · Estimated72.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · OfficialUsage entrée · par million de Tokens82 192 pointsUsage sortie · par million de Tokens136 987 points
通用文本向量-v1
Vérification en attente (UTC+8)
text-embedding-v1Modèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance58.3Valeur45.3
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEntrée vectorielle · par million de Tokens191 781 points
通用文本向量-v2
Vérification en attente (UTC+8)
text-embedding-v2Modèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance60.1Valeur46.6
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEntrée vectorielle · par million de Tokens191 781 points
通用文本向量-v3
Vérification en attente (UTC+8)
text-embedding-v3Modèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance63.4Valeur53.9
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEntrée vectorielle · par million de Tokens136 987 points
通用文本向量-v4
Vérification en attente (UTC+8)
text-embedding-v4Modèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance71.6Valeur59.6
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEntrée vectorielle · par million de Tokens136 987 points
视觉向量-flash
Vérification en attente (UTC+8)
tongyi-embedding-vision-flashModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.3Valeur · Estimated70.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEntrée vectorielle · par million de Tokens41 096 points
视觉向量-plus
Vérification en attente (UTC+8)
tongyi-embedding-vision-plusModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated62.3Valeur · Estimated53.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEntrée vectorielle · par million de Tokens136 987 points
Wan2.2-I2V-Flash
Vérification en attente (UTC+8)
wan2.2-i2v-flashModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated11.7Valeur · Estimated38.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentGénération vidéo 480P · par seconde27 398 pointsGénération vidéo 720P · par seconde54 795 pointsGénération vidéo 1080P · par seconde131 507 points
Wan2.2-I2V-Plus
Vérification en attente (UTC+8)
wan2.2-i2v-plusModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentGénération vidéo 480P · par seconde38 357 pointsGénération vidéo 1080P · par seconde191 781 points
Wan2.2-T2V-Plus
Vérification en attente (UTC+8)
wan2.2-t2v-plusModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated11.7Valeur · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentGénération vidéo 480P · par seconde38 357 pointsGénération vidéo 1080P · par seconde191 781 points
Wan2.5-I2V-Preview
Vérification en attente (UTC+8)
wan2.5-i2v-previewModèle indépendantAlibaba Cloud · AperçuAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance55.3Valeur46.8
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGénération vidéo 480P · par seconde82 192 pointsGénération vidéo 720P · par seconde164 384 pointsGénération vidéo 1080P · par seconde273 973 points
Wan2.5-T2V-Preview
Vérification en attente (UTC+8)
wan2.5-t2v-previewModèle indépendantAlibaba Cloud · AperçuAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance48.9Valeur42.3
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGénération vidéo 480P · par seconde82 192 pointsGénération vidéo 720P · par seconde164 384 pointsGénération vidéo 1080P · par seconde273 973 points
wan2.6-I2V-flash
Vérification en attente (UTC+8)
wan2.6-i2v-flashModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated54.9Valeur · Estimated60.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4arena · Independentarena · IndependentGénération vidéo 720P · par seconde82 192 pointsGénération vidéo 1080P · par seconde136 987 points
Wan2.1-I2V-Plus
Vérification en attente (UTC+8)
wanx2.1-i2v-plusModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated11.7Valeur · Estimated13.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentGénération vidéo 720P · par seconde191 781 points
Wan2.1-I2V-Turbo
Vérification en attente (UTC+8)
wanx2.1-i2v-turboModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated11.7Valeur · Estimated34.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentGénération vidéo 480P · par seconde65 754 pointsGénération vidéo 720P · par seconde65 754 points
Wan2.1-T2V-Plus
Vérification en attente (UTC+8)
wanx2.1-t2v-plusModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated11.7Valeur · Estimated13.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentGénération vidéo 720P · par seconde191 781 points
Wan2.1-T2V-Turbo
Vérification en attente (UTC+8)
wanx2.1-t2v-turboModèle indépendantAlibaba Cloud · StableAjout au catalogue (date de sortie à vérifier): 2026-09-10Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated11.7Valeur · Estimated34.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentGénération vidéo 480P · par seconde65 754 pointsGénération vidéo 720P · par seconde65 754 points
doubao-hitem3d-2-0-251223
Vérification en attente (UTC+8)
doubao-hitem3d-2-0-251223Instantané / version fixe · Accès uniqueHitem3D · StableAjout au catalogue (date de sortie à vérifier): 2026-09-09Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated82.2Valeur · Estimated57.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: doubao-seed3d-2-0-260328 · 82.2seed3d-public · OfficialUsage sortie · 3D · par million de Tokens21 917 809 points
doubao-hyper3d-gen2-260112
Vérification en attente (UTC+8)
doubao-hyper3d-gen2-260112Instantané / version fixe · Accès uniqueHyper3D · StableAjout au catalogue (date de sortie à vérifier): 2026-09-09Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated82.2Valeur · Estimated87.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: doubao-seed3d-2-0-260328 · 82.2seed3d-public · OfficialUsage sortie · 3D · par million de Tokens16 438 357 points
doubao-seedance-2-0-260128
Vérification en attente (UTC+8)
doubao-seedance-2-0-260128Instantané / version fixe · Accès uniqueByteDance · StableAjout au catalogue (date de sortie à vérifier): 2026-09-09Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.5Valeur · Estimated68.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.0-720p · 91.5arena · Independentarena · IndependentUsage sortie · Génération vidéo · par million de Tokens12 602 740 points
doubao-seedance-2-0-fast-260128
Vérification en attente (UTC+8)
doubao-seedance-2-0-fast-260128Instantané / version fixe · Accès uniqueByteDance · StableAjout au catalogue (date de sortie à vérifier): 2026-09-09Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.5Valeur · Estimated70.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.0-720p · 91.5arena · Independentarena · IndependentUsage sortie · Génération vidéo · par million de Tokens7 602 740 points
doubao-seedance-2-0-mini-260615
Vérification en attente (UTC+8)
doubao-seedance-2-0-mini-260615Instantané / version fixe · Accès uniqueByteDance · StableAjout au catalogue (date de sortie à vérifier): 2026-09-09Dernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.5Valeur · Estimated75.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.0-720p · 91.5arena · Independentarena · IndependentUsage sortie · Génération vidéo · par million de Tokens2 520 548 points
doubao-seedream-5-0-260128
Vérification en attente (UTC+8)
doubao-seedream-5-0-260128Instantané / version fixe · Accès uniqueByteDance · StableAjout au catalogue (date de sortie à vérifier): 2026-09-09Disponible · création et retoucheDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated54.4Valeur · Estimated53.4
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-4.5 · 54.4arena · Independentarena · IndependentUsage sortie · Image · par image60 274 points
GPT-4o Transcribe Diarize
Vérification en attente (UTC+8)
gpt-4o-transcribe-diarizeModèle indépendantOpenAI · StableAjout au catalogue (date de sortie à vérifier): 2026-08-28Disponible · outils audioDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated91.4Valeur · Estimated64.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentUsage entrée · Audio · par million de Tokens12 000 000 pointsUsage entrée · par million de Tokens5 000 000 pointsUsage sortie · par million de Tokens20 000 000 points
GPT Audio
Vérification en attente (UTC+8)
gpt-audioModèle indépendantOpenAI · StableAjout au catalogue (date de sortie à vérifier): 2026-08-28Capacités complètesDernière vérification du prixVérification en attente (UTC+8)
Performance · Estimated52.6Valeur · Estimated36.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · OfficialUsage entrée · par million de Tokens5 000 000 pointsUsage sortie · par million de Tokens20 000 000 pointsUsage entrée · Audio · par million de Tokens80 000 000 pointsUsage sortie · Audio · par million de Tokens160 000 000 points
Mistral Document AI 2512
Vérification en attente (UTC+8)
mistral-document-ai-2512Modèle indépendantMistral AI · StableAjout au catalogue (date de sortie à vérifier): 2026-08-28Dernière vérification du prixVérification en attente (UTC+8)
Performance96.1Valeur76.1
Provisoire
2026-10-08 16:22 (UTC+8) · Confidence 18%mistral-ocr · OfficialTraitement documentaire · par 1 000 pages6 000 000 points
Model Router
model-routerService de routage indépendantOpenAI · StableAjout au catalogue (date de sortie à vérifier): 2026-08-28Pas de prix fixe ; facturation selon le servicePerformance · Estimated50.0Valeur · Estimated50.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: o1-mini · 50.0Reference: qwen3.6-plus · 50.2Reference: gemini-2.0-flash-001 · 50.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentTarif dynamique : supplément d’entrée du routeur et points du modèle réellement choisi.
Descriptions des capacités vérifiées · 44
Claude Fable 5.1: complete within the verified, safely available deployment scope
Five adaptive efforts, high by default. Native/shared tools, structured output, real Codex continuation, image/PDF, cache and Key-owned files were verified.
- Five adaptive efforts, high by default. Native/shared tools, structured output, real Codex continuation, image/PDF, cache and Key-owned files were verified.
- Code execution uses the HCD free-combination billing bridge, adding fetch restricted to a non-resolving domain while preserving client tools. Execution/extremes are not live-tested (high-cost exemption); standalone native timing metering is not claimed.
- Performance71.6/value55.1 are estimates:7 direct and34 estimated metrics in the fixed41-panel, using exact LiveBench max data.
Claude Haiku 5.5：Complete within the verified deployment scope
The exact available scope is verified; optional parameters and resources retain explicit bounds.
- none disables thinking; low/medium/high/xhigh/max remain their real values; medium is the default. Native between_tools is rejected for this exact model.
- Native Messages and the shared Chat/Responses path, strict tool schemas, inline image/PDF, SSE and signed history passed. The actual Codex complete tools, MCP echo and saved-thread continuation passed.
- Bounded hosted search/fetch with citations and one-use owned remote MCP passed and settled once. Arbitrary remote URLs and unconstrained hosted execution are not enabled.
- Ordinary input, output, cache reads and 5m/1h writes have separate rates. Input including cache reads/writes above100K uses the whole-request long-context tier at5x; the threshold boundary was checked offline.
- The current deployment has no Files/Batch/container/skills API. Client function tools run on the client; no new native computer/browser toolset, durable background Responses resource or native compaction pass is claimed.
- 1M context and HCD128000 output limits retain safe reservation/settlement. Expensive extremes were not live-tested (high-cost exemption).
- Performance55.1 and value61.9 are estimated:8 directly attributed fixed-panel cells and33 estimates out of41. Benchmark effort high is separate from the medium inference default.
Claude Opus 5.5: complete verified deployment scope
Text, image/PDF, tools, thinking, cache and web access through Messages, Chat, Responses and Codex compatibility.
- Adaptive thinking is always on; medium is the default. Only temperature 1 is supported; top_p/top_k are unavailable.
- Verified client bridging supplies tool discovery. Native server tool search returned a safety refusal and is not claimed passed.
- 1M context and 128K output. Expensive limits are not live-tested (high-cost exemption).
- Files, Batch, code execution and native background jobs are not exposed. URL media generation is verified; token counting accepts supported inline inputs.
- Client-side compaction and same-thread continuation are verified; unpriced server compaction remains closed.
- Performance and value scores await exact-model evidence.
Claude Sonnet 5.5: complete within the verified, safely available deployment scope
Completion covers the exact model’s available scope. Optional hosted capabilities, resource quantities and budgets retain explicit bounds.
- none, low, medium, high, xhigh and max; high is default. none uses between_tools: no up-front thinking, while progress between tools is retained. none is never aliased to low.
- Native Messages and shared Chat/Responses conversion, strict structured output, advisory task-budget beta, functions, original SSE/signed thinking history, inline image/PDF, both cache TTLs and cache reads were verified.
- Actual Codex complete default tools, discovery, top-level composed-schema bridging, an in-memory MCP round trip and a persisted second turn passed. Advanced beta controls require the corresponding official header.
- Basic hosted search/fetch, citations and actual-usage accounting passed. No provider-native server Tool Search pass is claimed; client discovery bridging passed.
- A funded owned remote-MCP HTTPS echo and Key/project lifecycle were verified; its lease was closed. Arbitrary remote URLs, variable results and external credential management remain closed.
- The offering has no Batch, Files, code execution/containers/skills or new computer/browser toolsets. Messages has no native durable background-response resource. Native compaction remains closed; HCD’s existing client context path is reused without claiming an additional Sonnet compaction-generation live test.
- Official 1M context and 128K output use uniform full-context rates. Expensive extremes are not live-tested (high-cost exemption); offline limits, safe holds and settlement remain enforced.
- Performance 70.6 and value 61.1 are explicitly estimated: exact-model LiveBench observations cover 7 of the fixed 41-panel metrics at max effort. Value uses the same current official points tariff.
Codestral 2501: complete within the verified dedicated deployment scope
Verified Codestral-2501 native text chat, fill-in-the-middle, prefix/suffix completion, streaming and sampling through a dedicated code-tool entry.
- It is a text/code tool, not a function-tool-capable Codex main or subagent model.
- Exact FIM rejects metadata, prompt_cache_key and explicit null sampling/suffix values; HCD rejects them before dispatch rather than silently dropping them.
- Native responses and actual token usage are retained. Estimated scores are not derived from this interface acceptance.
Cohere Parse v5: complete within the verified dedicated deployment scope
Verified Cohere Parse v5 dedicated image parsing with text/Markdown, blocks, tables, image regions and coordinates. The public directory labels it preview.
- The Parse API accepts images only. PDF is rejected before upload; no hidden rasterization or fallback model is used.
- Image regions contain original source pixels from returned boxes, not generated images. This is document parsing, not ordinary chat.
Cohere Rerank v4.0 Pro: complete within the verified dedicated deployment scope
Verified Cohere Rerank v4.0 Pro dedicated multilingual document reranking with structured text, top_n, priority and ranked scores.
- Reranking only: chat and coding-agent requests are not admitted, regardless of misleading deployment metadata.
- The provider truncates document tails at max_tokens_per_doc; HCD does not rewrite source text and discloses that policy. Estimated scores are separate from capability acceptance.
decision-model-preview: Full structured decisions (verified deployment scope)
Classification, yes/no probabilities and ordinal scoring preserve original probabilities, confidence and input usage; no chat text is generated.
- Text, object or array state. HCD:1–16 questions, up to255 choices,2–10 score levels,32768 UTF-8 bytes total. Provider input context:65536 tokens.
- Rounded probabilities and sums remain unchanged, without normalization. Confidence is not verified accuracy. Currently limited-time free; normal account/Key authorization, metering and single settlement apply.
- No chat, streaming, tools, search, cache, Batch, media or persistent jobs. Maximum context not live-tested (high-cost exemption). Generic fixed-panel estimate:0/41 direct coverage, not decision accuracy; value uses this model own input tariff and decision workload.
DeepSeek V4.1 Flash: complete within the verified dedicated deployment scope
Verified DeepSeek Flash text reasoning, tools, streaming/history/cache, native Chat prefix FIM and image input within the exact deployed scope.
- Image files use Key-owned authorization and lifecycle handling; compatibility media URLs require HTTPS. Hosted web/file search, native namespace discovery, encrypted reasoning and native background jobs are not exposed.
- Official maximum context/output and large-media bounds use guards and offline checks; expensive extremes are not live-tested (high-cost exemption).
- Earlier 74.9/75.3 figures were incomplete-panel estimates, not exact-model acceptance scores. Public composite performance/value scores await exact evidence.
- Current exact protocol output bounds:393216 tokens for Chat/Responses and4096 for FIM. Former384000 corrected from exact schema; no extreme live test.
DeepSeek V4 Pro: complete in the verified deployment scope
Verified text, structured output, reasoning, functions/client tool discovery and real Codex continuation; native Chat streaming/Prefix, Messages and FIM.
- Hosted web search, image/file input and upstream stored/background state are unsupported; the model profile disables web search.
- Performance69.3 and value65.7 are estimates:7 exact0813 public metrics and34 estimates in the fixed41-metric panel.
- Maximum context/output/concurrency: not live-tested (high-cost exemption); official limits and offline guards apply.
- Current exact protocol output bounds:393216 tokens for Chat/Responses and4096 for FIM. Former384000 corrected from exact schema; no extreme live test.
doubao-deepseek-v4-1-flash: verified deployment scope
Text, image and video; four reasoning levels, JSON Schema, functions, streaming and saved history. Actual Codex tools and continuation verified. Native remote MCP and owned Responses; HCD owned-file and controlled web-search bridges.
- Context 1,048,576 tokens; input maximum 1,048,576; default/maximum output 393,216 including thought, within the combined context. Compatibility image limit 1,500; native 3,600; each media item 50 MiB, request 64 MiB. Owned inline files: 5 MiB each, 24-hour retention.
- Implicit cache is metered. Explicit cache, native hosted search, Flex, Batch and background generation are closed and rejected. HCD MCP search reserves and bills separately. Actual Work client remains unverified. Performance 77.5/value 76.8 are estimates over 41 metrics, 12 direct model sources, no direct offering benchmark. Expensive boundaries checked offline.
doubao-DeepSeek V4 Flash GA (2026-07-31) — Full integration (verified deployment scope)
Verified text, none/low/high/max, JSON Schema, functions, bounded search, full tool history, MCP, implicit/explicit cache and native response resources. Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch.
- Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch.
- Default low. Deleting a response does not end cache storage liability before TTL. Performance56.6/value58.8 estimated,0/41 direct; high-cost extremes not live-tested.
- Account points/M tokens, standard input/output/cache:821918/2465753/27397; flex:410959/1232877/27397. No extra token cache-write fee. Storage4658 points/M-token/hour; search5480 points/call. Key multiplier and per-item rounding apply separately.
doubao-DeepSeek V4 Pro GA (2026-08-13) — Full integration (verified deployment scope)
Verified text, none/low/high/max, JSON Schema, functions, bounded search, full tool history, MCP, implicit/explicit cache and native response resources. Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch. Flex returned upstream ModelLoading and is not verified or open; rejected before dispatch. Its reviewed rate is reference only. Cache continuation must explicitly stay within the original TTL; cross-model references, context edits and native hosted tools are rejected. Missing reasoning breakdown keeps a funded storage upper bound without posting an estimated charge.
- Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch.
- Default low. Deleting a response does not end cache storage liability before TTL. Performance59.4/value56.2 estimated,7/41 direct; high-cost extremes not live-tested.
- Account points/M tokens, standard input/output/cache:2465753/7397260/82192; flex:1232877/3698630/82192. No extra token cache-write fee. Storage4658 points/M-token/hour; search5480 points/call. Key multiplier and per-item rounding apply separately.
- Flex returned upstream ModelLoading and is not verified or open; rejected before dispatch. Its reviewed rate is reference only. Cache continuation must explicitly stay within the original TTL; cross-model references, context edits and native hosted tools are rejected. Missing reasoning breakdown keeps a funded storage upper bound without posting an estimated charge.
FLUX.2 Pro: complete within the verified dedicated deployment scope
Verified FLUX.2 Pro dedicated image generation, editing and up to eight reference images. The public directory currently marks it as planned.
- PNG/JPEG output and the model-specific prompt enhancement mapping were checked; tuning fields from another model are explicitly rejected.
- Image streaming, transparent output, mask editing and steps/guidance controls are outside this exact interface. Image acceptance is neither a quality score nor a chat-route claim.
Google Gemini 3.8 Flash-100: fully reviewed deployed scope
Native GenerateContent, Chat and Interactions support text, image, audio, video and PDF input, thinking, JSON, functions, streaming and continuation. Codex uses the HCD Responses bridge.
- Knowledge Studio adds isolated Python (NumPy, SymPy and Matplotlib), URL reading, video-frame inspection and controlled web search. These are HCD bridges; native hosted code, search and AGENTIC video loops are not enabled. Computer use returns proposed actions only.
- Combined context: 1,048,576 tokens; no disclosed independent input maximum. Default and maximum output: 65,536 tokens including thinking, subject to remaining context. Explicit cache read/delete/expiry and owned HCD files, background responses and Batch preserve original results. Batch uses standard call prices.
- Per million tokens: input 3,000,000 points, cache hits 300,000 and output including thinking 15,000,000. Explicit cache creation uses the input rate; storage costs 2,000,000 points per million token-hours. Supplier promotional credits have not been received and do not promise customer refunds. Performance 76.6 and value 66.1 are estimates: 12 model-wide public metrics and 29 estimated metrics, with no direct performance measurement for this offering. Expensive limits were checked offline.
- Work Responses live web search uses an HCD controlled bridge. In auto mode the model decides whether to search, at most once per response; model and search usage are metered separately from original receipts. Authenticated actual Work client and search roundtrip verification remains pending.
- Gemini 3.8 Flash-100 supports HCD summary views: auto keeps the provider automatic summary; detailed shows the full available provider summary; concise explicitly shows an HCD bounded extract and truncation status; none hides the public summary. These views do not control provider summary length or add model calls. Thinking tokens retain original receipt billing. Actual remote Work roundtrip verification is pending.
Gemini 3.8 Live-100 · Current deployment fully integrated
Realtime audio/video, camera/images, prebuilt Avatar, function follow-ups, native resume, interruption and bounded web search.
- Custom Avatar is unavailable on this deployment and rejected before provider contact. The user explicitly deferred and exempted it from full certification; no application was submitted.
- Search and automatic VAD use bounded HCD bridges; provider-native search is not exposed.
- Google supplier rates per1M tokens: TEXT/IMAGE-VIDEO/AUDIO input0.75/1/3USD; TEXT/AUDIO/VIDEO output4.5/12/1USD. Thinking uses text-output rates; transcription and retained history remain in original meters. Search has a separate quote.
- Performance77.2 and value84.0 are estimates; direct panel coverage0/41. Audio/Avatar quality not benchmarked. Extreme contexts/media: not live-tested (high-cost exemption).
Google Gemini 4 Argon: verified deployed capabilities
Text, image, audio, video and PDF input; three reasoning levels, JSON, function tools and streaming. Codex tools and continuation are verified. HCD knowledge tools provide isolated Python, URL reading, video-frame inspection and separately billed controlled search. Responses builtin web_search uses the bounded HCD compatibility bridge; actual Work client verification remains pending. Preview search and unmapped explicit controls are rejected.
- Combined context is 1,048,576 tokens; the independent input limit is not disclosed. Native GenerateContent defaults to and permits 1,048,576 total output tokens through manual owner-bound continuationToken requests; each segment permits 32,768 non-streaming or 65,536 streaming tokens. Responses, Chat and Interactions default and maximum per-call outputs are 32,768 non-streaming / 65,536 streaming, including reasoning within combined context. Explicit cache is unsupported; implicit cache is metered. Owned HCD files, background responses and Batch retain lifecycle controls; Batch uses standard call prices.
- Per million tokens: 8,000,000 input points, 400,000 cache-hit points and 40,000,000 output/reasoning points. Full input, output and tool liabilities are reserved against both account and Key before submission; each explicit continuation is separately reserved and settled. Performance 77.2 and value 62.5 are estimates: 6 model-wide public metrics plus 35 estimates in a fixed 41-metric panel, with no direct offering performance measurement. Expensive boundaries were checked offline. Supplier promotional credits are not treated as received.
Gemini Nano Banana 2.1-100: Complete within verified deployment scope
Complete verified image-studio scope; HCD bounds are distinct from manufacturer maxima.
- Image generation/editing, streaming and private-reference continuation; 1K/2K/4K, 15 aspect ratios, minimal/medium/high, up to32768 output tokens and native system instructions. One PNG/JPEG result per request.
- Up to14 PNG/JPEG/WebP/HEIC/HEIF references:7MiB each,40MiB combined media,64MiB complete request/history. One PDF/UTF8 file up to8MiB/30 PDF pages, or one silent MP4/WebM up to16MiB/60s with crop and fps(0,24].
- HCD controlled webpage/source-image search with sources, not Google native search or an image index. The cumulative50 CNY platform risk allowance uses conservative metered supplier upper bounds:30 CNY held per request, concurrency1; new search may stop before actual spending reaches50 CNY. It is not customer credit, free usage or an upstream bill cap.
- Search and image components settle once from their original receipts. A successful search may remain charged when later image processing fails. Submitted jobs and result reading continue after the risk stop; ordinary generation/editing works independently.
- HCD durable batches support create, disconnect, undispatched restart, status, cancellation and results.1..2 sequential items only:1K/1:1/minimal ormedium/max4096 output/one PNG-JPEG reference/no search. Standard realtime per-item rates apply, without Google native Batch discounts.
- Native countTokens is advisory, not generation billing or the sole reservation bound. Input, implicit cache reads, text/thought output and image output are metered separately. Explicit cache/file URI/YouTube/native Batch storage are unavailable; upstream audio/function calling/structured output are unsupported. Original image bytes and provider provenance are preserved.
- 4K and maximum context/output/14-reference extremes: not live-tested (high-cost exemption); exact model evidence and offline resource boundaries verified. Performance92.5 comes from two public image benchmarks; value66.5 is estimated from standard prices, not route performance testing.
GPT-5.6 Luna: complete within the verified safe deployment scope
The exact model is integrated across its verified safe deployment scope. Expensive limits and unpriced optional hosted features retain explicit restrictions.
- Text and image input with text output; reasoning supports none, low, medium, high, xhigh and max, with medium as the default. Structured output, functions, real Codex default tools and a saved-history second turn were verified.
- Raw streams and cache metering, background completion after disconnect, owned GET, replay and DELETE were accepted. WebSocket supports a verified two-response response.create chain; mid-response steering is unavailable for this model.
- A small valid image was tested for transport, meaning and metering. Bounded images reserve the full documented image-token ceiling. Unknown media and files retain strict liability bounds and may be rejected before dispatch when funds are insufficient.
- The long-context tier starts above 272,000 total input tokens, including cache, and prices the whole request. Account and Key calculations for input, cache reads, cache writes and output were checked offline across the boundary. Maximum context/output, live threshold crossing and large media are not live-tested (high-cost exemption).
- Pro, multi-agent work, arbitrary remote MCP, indexed search, containers, hosted tools and image generation remain closed where price or lifecycle bounds are unverified. Parameters are not silently discarded. Model audio/video input and direct non-text output are unsupported.
- Current performance 64.2 and value 65.8 derive from public evaluations and coherent pricing, not an HCD live quality score.
GPT-5.6 Sol: complete within the verified safe deployment scope
Completion covers the exact model and verified safe deployment. Optional hosted capabilities and expensive boundaries retain explicit limits. Reservations, settled charges and unresolved liability stay separate.
- Text and image input with text output; reasoning supports none, low, medium, high, xhigh and max, with medium as the default. Structured output, native Chat functions with explicit none, Responses functions, real Codex default tools and two-turn saved history were verified.
- Raw streams, cache writes and reads, background completion after delivery disconnect, owned GET, stream replay and DELETE were accepted. WebSocket scope is text, low/default, 64 output tokens, one ordinary response.create continuation and two responses. This model does not support response.steer. The connector continues to use HTTP/SSE.
- A small valid image was tested for transport, meaning and metering. Bounded images reserve the full documented image-token ceiling. Unknown media and files retain strict full-context liability or are rejected before provider contact when funds are insufficient.
- The long-context tier starts above 272,000 total input tokens, including cache, and applies to the whole request across input, cache reads, cache writes and output. Account and Key math was checked offline on both sides of the threshold. Maximum context/output, live threshold crossing and large media are not live-tested (high-cost exemption).
- Pro, multi-agent, arbitrary remote MCP, indexed file search, containers, hosted Shell/Skills, hosted image generation and unverified sampling parameters remain closed; no parameter is silently discarded. Model audio/video input and direct non-text output are unsupported.
- Existing performance 88.2 and value 70.5 use public evaluation evidence and coherent reviewed pricing, not HCD live quality scores.
GPT-5.6 Terra: complete within the verified safe deployment scope
The exact model is integrated across its verified safe deployment scope. Expensive limits and unpriced optional hosted features retain explicit restrictions.
- Text and image input with text output; reasoning supports none, low, medium, high, xhigh and max, with medium as the default. Structured output, functions, real Codex default tools and a saved-history second turn were verified.
- Raw streams and cache metering, background completion after disconnect, owned GET, replay and DELETE were accepted. WebSocket supports a verified two-response response.create chain; mid-response steering remains closed pending exact-model verification.
- A small valid image was tested for transport, meaning and metering. Bounded images reserve the full documented image-token ceiling. Unknown media and files retain strict liability bounds and may be rejected before dispatch when funds are insufficient.
- The long-context tier starts above 272,000 total input tokens, including cache, and prices the whole request. Account and Key calculations for input, cache reads, cache writes and output were checked offline across the boundary. Maximum context/output, live threshold crossing and large media are not live-tested (high-cost exemption).
- Pro, multi-agent work, arbitrary remote MCP, indexed search, containers, hosted tools and image generation remain closed where price or lifecycle bounds are unverified. Parameters are not silently discarded. Model audio/video input and direct non-text output are unsupported.
- Current performance 73.8 and value 62.9 derive from public evaluations and coherent pricing, not an HCD live quality score.
GPT-6 Astra: complete within the verified, safely available deployment scope
Completion covers the verified deployment scope, not every optional hosted capability. Known prices and provable quantity bounds govern availability. Holds and settled charges remain separate; authorization and budget gates remain active.
- Verified text, low/medium/high/xhigh/max reasoning, structured output, Responses functions/namespaces/parallel and async tools, tool search, client computer/patch protocols, streaming, saved and encrypted history, cache, compaction and background resource lifecycle. Actual Codex default tools and saved-history continuation were independently tested.
- PNG and bounded simple single-frame WebP/non-animated GIF were verified. The latter use low detail, dimensions up to 512 pixels and files up to 1 MiB. JPEG transport and metering passed, but a red fixture was described as Purple; that semantic case failed. Unknown media and remote URLs retain strict holds or rejection.
- WebSocket scope is text, low reasoning, 64 output tokens, one queued steer and an automatic second response. The original response completes normally; immediate interruption and unverified tool/history combinations are not enabled.
- The deployment rejects temperature on native Responses, and logit_bias/function tools on native Chat. Local guards remain. Other sampling controls and max_tokens are not verified; use max_completion_tokens for Chat and max_output_tokens for Responses.
- file_search index size and retention bounds remain unresolved. Code Interpreter/container pricing has conflicting minute versus Session units. Pro/multi_agent aggregate quantities and costs lack proven bounds. These features remain restricted or disabled.
- Hosted remote MCP was tested only with an owned fixed HTTPS echo, same-Key/project approval and two metered responses. Its temporary entry is closed. Arbitrary remote servers, variable results, credentials and broader lifecycle are not enabled; local MCP tests are not substitutes.
- Batch, Flex and Fast/Priority are not offered by this deployment. Audio/video input and direct media output are outside its verified scope. Unavailable hosted image generation, Shell/Skills and other optional tools remain gated.
- The 272,000-token tier uses total input including cache. An actual 272,022-input-token long-tier receipt was verified. Maximum context/output and other expensive boundaries retain offline checks and explicit high-cost live-test exemptions, not claims of maximum-size live generation.
GPT-6 Luna: complete within the verified, safely available deployment scope
Completion covers the verified safe deployment. Optional upstream features remain limited where bounds are unproved. Reservation and settlement stay separate, with exact-model authorization and cost gates.
- Verified text, default medium and none/max, structured output, original streams, Chat functions with none, Responses async functions, a small image semantic case, actual Codex default tools and in-memory MCP across two turns, cache usage, background disconnect/completion/retrieve/stream replay/delete, and bounded WebSocket steering with two responses.
- Reasoning choices are none, low, medium, high, xhigh and max, with medium as default. Chat functions require explicit none; max uses Responses.
- WebSocket is limited to native text, low reasoning, default tier, 64 output tokens, one queued steer and two responses. The connector uses HTTP/SSE.
- Maximum context/output, long-context threshold, large media and high-output compaction use official limits and offline checks: not live-tested (high-cost exemption). A small image was tested, but unknown media retains full-context reservation; no low-cost image bound is claimed.
- Pro, multi-agent, automatic compaction, arbitrary remote MCP, indexed file search, containers and hosted Shell/Skills stay restricted where safe cost or lifecycle bounds are unproved. Model audio/video input and direct non-text model output are unsupported. Unverified sampling parameters are explicitly rejected.
- Some exact-model public benchmarks exist, but the fixed 41-cell scoring panel has not passed a like-for-like review. Composite performance and value scores remain pending; no other model's estimate is reused.
GPT-6 Sol: complete within the verified, safely available deployment scope
Completion covers the verified safe deployment, not all optional official capabilities. Reservation bounds and actual settlement remain separate; exact-model authorization and cost gates remain active.
- Verified text, default medium and none/max parameters, structured output, original streams, Chat function calling with none, Responses async functions, actual Codex default tools and in-memory MCP with two persisted turns, cache usage, and background disconnect/completion/replay/retrieve/delete.
- Reasoning choices are none, low, medium, high, xhigh and max, with medium as the model default. Chat functions require explicit none; max uses Responses.
- WebSocket availability is native text with low reasoning, default tier, 64 output tokens, one queued steer and two responses. The connector continues to use HTTP/SSE.
- Maximum context/output, long-context thresholds, large media and high-output compaction use exact official limits and offline boundary checks: not live-tested (high-cost exemption). Unknown media retains full-context reservation; no low-cost or live image-understanding claim is made.
- Conflicting official sampling descriptions remains unresolved, so those parameters are rejected. Pro, multi-agent, automatic compaction, arbitrary remote MCP, indexed file search, containers and hosted Shell/Skills remain restricted where safe cost or lifecycle bounds are unproved. Model audio/video inputs and direct non-text model outputs are unsupported.
- Composite performance and value scores are marked estimated: 13 of 41 panel cells have exact-model public observations and 28 use same-metric peer estimates. These are not HCD deployment tests. Value uses reviewed public account-point rates, not actual charges. Rankings against GPT-5.6 Sol and other models apply only to this fixed panel; overlapping estimate ranges do not establish general capability order. Image semantics and dedicated tool-search/computer/apply-patch semantic cases were not separately live-tested.
GPT-6.1 Sol: complete within the verified deployment scope
The exact model is integrated across its currently verified scope. Expensive boundaries and unpriced hosted capabilities retain explicit restrictions.
- Text and image input, text output. Five reasoning efforts: low, medium, high, xhigh and max; medium is default. none/minimal and native Chat tool calling are unsupported; use Responses for tools.
- Strict structured output, functions and async options, streams and cache metering, real Codex default tools, an in-memory MCP round trip and a persisted second turn were verified.
- Background completion after delivery disconnect, owned GET, stream replay and DELETE were verified. Narrow WebSocket allows one ordinary response.create continuation; steer remains pending and closed. Codex uses HTTP/SSE.
- Points use the user-approved exact-model official tariff as an estimate. Supplier formal rates remain unconfirmed. Estimated pricing is used for reservation and account/Key service settlement, not confirmed supplier charges.
- The whole request switches to long-context pricing above 272,000 total input tokens including cache. Maximum context/output, threshold crossing and large media are not live-tested (high-cost exemption); official limits and offline boundaries apply.
- Unknown media/files retain full-context liability bounds and are rejected before dispatch when budgets are insufficient. Unpriced Pro, multi-agent, automatic compaction and hosted resources stay closed. Performance and value await exact numerical evidence.
GPT Audio: complete within the verified dedicated deployment scope
Verified dedicated audio inference with text/audio input and text/audio output, streaming and function calls. The public directory currently marks this entry as planned; access depends on the actual entry permissions.
- This is acceptance of the exact audio interface, not a general Codex conversation-model claim. Image I/O, realtime sockets, structured-output schemas and discounted prompt cache are outside the verified scope.
- Signed input limits bound resources; unsupported parameters are rejected before submission. Capability acceptance is not a quality benchmark, and directory scores retain their stated evidence grade.
GPT Audio 1.5: complete within the verified dedicated deployment scope
Verified GPT Audio 1.5 dedicated audio inference: text/audio input and text/audio output, streaming and function calls. The public directory currently marks it as planned.
- Acceptance covers this exact audio interface; it does not activate a general Codex chat route. Images, realtime sockets, structured-output schemas and discounted cache pricing are outside scope.
- Signed input contracts bound resources and reject unsupported parameters before submission. Directory scores are separate from this capability acceptance.
GPT Audio Mini: complete within the verified dedicated deployment scope
Verified GPT Audio Mini dedicated text/audio I/O, streaming and function calls. The public directory currently marks it as planned.
- This is not a general Codex chat integration. Image I/O, realtime sockets and structured-output schemas are outside scope.
- Cache hints and native usage reporting were verified, but live calls reported zero cached tokens; no actual hit or discount was proven. Unpublished discounted rates are not guessed.
- Functional acceptance is not a quality benchmark; estimated directory scores remain estimates.
GPT Live Transcribe: complete within the verified dedicated deployment scope
Verified dedicated live audio transcription with context hints and streaming. The public directory currently marks it as planned.
- This is a transcription entry, not general chat, function tools, a file-transcription endpoint or audio generation.
- Signed contracts bound inputs and reject unsupported fields; capability acceptance is not a transcription-quality score.
GPT Realtime: complete within the verified dedicated deployment scope
Verified dedicated realtime text/audio/image input, text/audio output, streaming, functions and prompt caching. The public directory currently marks it as planned.
- The entry uses HCD browser audio transport and a WebSocket proxy; it does not establish full WebSocket support for ordinary Codex chat clients.
- Generated image/video output, structured-output schemas, reasoning-effort control, external SIP and hosted remote MCP are not offered. Functional acceptance is not a quality score.
GPT Realtime 1.5: complete within the verified dedicated deployment scope
Verified GPT Realtime 1.5 dedicated realtime text/audio/image input, text/audio output, streaming, functions and caching. The public directory currently marks it as planned.
- Acceptance covers browser audio transport and its WebSocket proxy, not full WebSocket capability in general Codex clients.
- Generated image/video output, structured-output schemas, reasoning-effort control, external SIP and hosted remote MCP are unavailable; directory scores are separate from this acceptance.
GPT Realtime Mini: complete within the verified dedicated deployment scope
Verified GPT Realtime Mini dedicated realtime text/audio/image input, text/audio output, streaming, functions and caching. The public directory currently marks it as planned.
- Scope is browser audio transport and its WebSocket proxy, not full WebSocket support for ordinary Codex clients.
- Generated image/video output, structured-output schemas, reasoning-effort control, external SIP and hosted remote MCP are unavailable. Capability acceptance and estimated scores are separate.
Grok 4.7 — Full verified deployment scope
Native Chat, automatic-reasoning Responses and a four-effort Codex Chat bridge support text/images, JSON, tools and saved-thread history.
- low, medium, high and xhigh passed live; high is the default and none is unsupported. Codex uses the Chat bridge; native Responses uses automatic reasoning.
- Output includes reasoning tokens. Input including cache reads above200000 tokens applies the2x long-context tariff to the whole request. Cache hints are explicitly not forwarded; cache hits are not promised.
- Actual full Codex tools, MCP echo and saved-thread continuation passed. Performance70.3 and value61.4 are estimates with0/41 direct coverage. Expensive context/media limits were not live-tested.
- No provider-hosted Web/X/code tools or encrypted state claimed for this deployment. Google-100 has its own reviewed scope and prices.
- xAI states No text output limit: no separate text-output cap. The500000 combined context still applies; HCD uses a finite supported ceiling and upstream actual-token handling, never reduces the default using fee estimates or claims a second independent500000 output budget.
Google Grok 4.7-100 — Fully reviewed deployed scope
Native Responses and Chat: text/images, four reasoning levels, JSON, complete tools and encrypted continuation.
- low, medium, high and xhigh reviewed; high is the default and reasoning cannot be disabled. Adjustable native Google Responses was live verified.
- Actual connector-generated Codex configuration, complete tools, MCP echo and same saved-thread continuation passed. Encrypted reasoning was replayed unchanged; cache keys and real cache hits were verified.
- Performance70.3 and value61.4 are estimates, direct coverage0/41. Expensive context/media extremes were checked offline. Provider-hosted Web/X/code tools, Batch, upstream files, reasoning summaries and cache retention are not exposed.
- Combined context524288 tokens; independent output maximum not disclosed. HCD context_bound support and default are constrained by remaining context, not a published independent output maximum.
MAI Thinking 1: complete within the verified dedicated deployment scope
Verified MAI Thinking 1 native text reasoning, function tools, history continuation, streaming/nonstreaming and token usage for a dedicated text-tool conversation.
- The Responses bridge validates a complete result before replay; incremental Responses delivery is not implemented. Native API streaming preserves original events.
- The directory labels it preview. Client support follows the verified entry and does not imply that every Codex function is exposed.
Mistral Medium 3.5: complete within the verified dedicated deployment scope
Verified Mistral Medium 3.5 native text/image input, text chat, JSON objects, streaming, multiple candidates and sampling through a dedicated text/code-tool entry.
- The exact hosted offering does not advertise tool calling; HCD rejects tool fields before generation and does not present it as an ordinary Codex tool agent.
- Explicit temperature=null or top_p=null is rejected locally after upstream rejection; omission uses defaults. The directory labels it preview, and estimated scores are separate.
Mistral OCR 4: complete within the verified dedicated deployment scope
Verified Mistral OCR 4.0 dedicated image/PDF recognition, text/table/image extraction, layout, page selection and multilingual OCR. This is a document entry, not a chat model.
- The exact deployment accepts token, word and page confidence granularity; upstream rejects block granularity with 422, so it is rejected before submission.
- The public directory labels it preview. Capability acceptance and performance/value score evidence remain separate.
通用多模态向量: complete within the verified dedicated deployment scope
Verified Multimodal Embedding v1 dedicated independent text, image and video vectors with ordered mixed batches. The public directory currently marks it as planned.
- At most 20 inputs per batch, each producing a fixed 1024-dimensional vector. The provider processes at most 512 tokens per text item and truncates longer text; HCD preserves the submitted text and discloses this behavior.
- Dense output, image URL/local input and relevant parameter forwarding are supported. No measured retrieval gain, modality fusion, variable dimensions, streaming or async Batch is claimed.
- Performance 62.3 and value 48.1 remain low-confidence estimates, not direct exact-model evaluation. Media reservations and settled charges are separate.
qwen-DeepSeek-V4-Flash-0731：Verified integration (currently open scope)
Full integration within the verified open deployment scope: text, none/low/high/max, structured output, functions, complete default Codex tools, pure in-memory MCP, explicit saved-thread continuation and implicit cache. Hosted search/extraction/interpreter and native storage/response-ID/conversation/background are closed and explicitly rejected before provider dispatch.
- Closed because aggregate agent iteration/charge bounds are unverified. max_output_tokens limits reply only; undocumented max_tool_calls is not a hard cap. The separate393216 reasoning-token maximum is reserved; high-cost extremes are not live-tested.
- Original search receipts and historical charges are preserved; hosted search is currently closed. Own prices and scores unchanged.
- Current official reply/reasoning total shares393216; reservation uses that shared ceiling, preserving separate raw usage and once-only settlement.
qwen-DeepSeek-V4-Pro · Verified open deployment scope
Full integration within the verified open deployment scope: text, none/high/max, structured output, functions, complete default Codex tools, pure in-memory MCP, explicit saved-thread continuation and implicit cache. Hosted search/extraction/interpreter and native storage/response-ID/conversation/background are closed and explicitly rejected before provider dispatch.
- Performance 61.3, value 56.9: estimated fixed panel with 7 model-wide public observations and 34 estimates. Own standard tariff 3287671/6575342/cache273973 points per million tokens; no peak/off-peak tariff. Provider alias has no declared immutable snapshot. Separate Responses thinking reservation uses a conservative deployed output upper bound; expensive limits not live-tested. Supplier invoice cash remains unknown.
- Current official reply/reasoning total shares393216; reservation uses that shared ceiling, preserving separate raw usage and once-only settlement.
qwen-DeepSeek-V4-Pro-0813 · Verified open deployment scope
Full integration within the verified open deployment scope: text, none/low/high/max, structured output, functions, complete default Codex tools, pure in-memory MCP, explicit saved-thread continuation and implicit cache. Hosted search/extraction/interpreter and native storage/response-ID/conversation/background are closed and explicitly rejected before provider dispatch.
- Closed because aggregate agent iteration/charge bounds are unverified. max_output_tokens limits reply only; undocumented max_tool_calls is not a hard cap. The separate393216 reasoning-token maximum is reserved; high-cost extremes are not live-tested.
- Performance71.7/value67.7 estimated;7 exact public model metrics and34 estimates in41 fixed panel. Value uses this offering's reviewed off-peak base workload; cache separate. Off-peak22:00–08:00 UTC+8; peak token rates x2. Supplier invoice cash unknown.
- Current official reply/reasoning total shares393216; reservation uses that shared ceiling, preserving separate raw usage and once-only settlement.
Qwen-Image-2.1-Pro：complete within the verified deployment scope
Image-studio-only model; completion covers verified generation, editing, parameters, metering and native task lifecycle.
- Unified generation/editing, up to10 reference images and1–6 outputs; transparent images, seed, prompt enhancement, Direct/Agent, enable_thinking and watermark. Agent is generation-only.
- Static PNG/JPEG/WebP/BMP/TIFF/GIF inputs; native PNG output, with HCD JPEG/WebP conversion. Masks guide reference editing; HCD completion events are not native partial-image streaming.
- Native async tasks return result_ref and continue after client disconnect. Original usage settles once; same-Key original-result reads are free. Provider results expire after24 hours; save returned images.
- HCD bounds:18,000 prompt characters,10MB per image,64MiB aggregate,40M input pixels,8000-pixel sides and10:1 input ratio. Output area512²–2048² and ratio1:8–8:1. Six-output/ten-reference extremes use offline checks and high-cost live exemptions.
- No ordinary Chat, function tools, web search, context cache or native Batch inference. Performance is a same-family public-data estimate, separate from functional acceptance.
Qwen3-VL-Rerank: complete within the verified dedicated deployment scope
Verified Qwen3 VL Rerank synchronous text, image, video and mixed-input reranking. The public directory currently marks it as planned.
- Image queries, top_n, instructions, returned documents and native responses are supported. Video fps is strictly 0 < fps <= 1; exact deployment rejects zero and HCD rejects it before provider dispatch.
- Official 4,000 query and 8,000 per-item token descriptions conflict. Exact limits remain upstream-enforced pending clarification; no invented truncation is applied.
- 493154 points per million tokens for video-containing requests is an approved liability estimate, not a published supplier tariff or verified supplier cost. This synchronous entry has no streaming, Batch or file jobs.
千问3.7-通用文本重排序: complete within the verified dedicated deployment scope
Verified Qwen3.7 Text Rerank synchronous text reranking, instructions, top_n, all results and large candidate sets. The public directory currently marks it as planned.
- Each document is limited to 50,000 characters; over-limit input is rejected before submission without truncation.
- This dedicated reranking entry has no image/video, streaming, hosted tools, uploaded files or async jobs. Parameters from other models are not substituted. Estimated scores are not quality results from this acceptance.
LIMITE ACTUELLE
Limite actuelle
Ajout de 32 modèles hors Google : 27 modèles texte, Mistral Document AI, trois modèles de plongements et Sora 2. Installez le connecteur 1.0.86.0 et activez chaque plugin et permission de clé API. API texte : 34 modèles ; menu Codex : 32 avec outils. Phi et Llama sont réservés aux questions via API. Documents : 30 Mo et 30 pages. Recherche dans les textes locaux sélectionnés avec citations et index réutilisables. Vidéo : 4/8/12 secondes, 720p, images de référence et remix de vidéos terminées. Téléchargez rapidement les vidéos. Facturation de l’usage terminé ; lecture du cache gratuite. Google et model-router restent exclus. Identités, protocoles, données, agents et commandes restent dans l’environnement local, edge ou privé autorisé par le client. Le site public présente le service ; ce n’est pas une plateforme cloud de contrôle d’équipements.