HENGCDHENGCD INDUSTRIAL AI
ProjektanfrageAnmelden

MODEL PRICING

Klare Modellpreise und Punkte

Modellpreise, Connector-Integration und Verfügbarkeit stehen auf einer Seite. Der tatsächliche Zugriff hängt von API-Schlüssel und Serverroute ab.

01

Seitenumfang

Modellpreise, Connector-Integration und Verfügbarkeit stehen auf einer Seite. Der tatsächliche Zugriff hängt von API-Schlüssel und Serverroute ab.

Diese Seite ist eine übersetzte Übersicht. Für technische und vertragliche Details gilt die chinesische Fassung.

Öffentlicher Katalog613Modelleinträge einschließlich Kandidaten
HCD Codex Connector91Modelle gelistet
Bildstudio25Modelle gelistet
Audiostudio17Modelle gelistet
Echtzeit-Sprachstudio7Modelle gelistet
Videostudio32Modelle gelistet
Dokumentenstudio6Modelle gelistet
Wissensstudio26Modelle gelistet
3D-Studio3Modelle gelistet
Text- und Code-Studio2Modelle gelistet

Die Zahlen basieren auf den veröffentlichten Modelllisten. Jedes Modell wird je Studio einmal gezählt und kann in mehreren Studios vorkommen. Zugriff und Funktionen richten sich nach API-Schlüsselrechten, Serverrouten und den jeweiligen Modellangaben.

Completed capability declarations: 44. Each covers its stated deployment scope; model notes retain limits and pending items.

Token-Tarife gelten pro Million Token. Andere Funktionen verwenden die angegebene Einheit. Kontext- und Verarbeitungsstufen folgen dem jeweiligen Modelltarif. Das Konto wird nach tatsächlichem Verbrauch belastet; der API-Key-Faktor gilt nur für Key-Punkte. Freigegebene Dienste verbrauchen Punkte nach tatsächlicher Nutzung. Online-Aufladung und Rechnungsausstellung sind weiterhin nicht verfügbar.

ModellPunkteverbrauch

Eigenständige Modelle werden bevorzugt. Ein Snapshot oder Alias wird nur aufgenommen, wenn er der einzige verfügbare Zugang derselben Plattform, Generation und Funktionsfamilie ist. Alle Typen zeigt weitere Versionen mit eigenen Kennungen, Preisen und Verfügbarkeiten. Fehlende Belege oder ungeklärte Beziehungen bedeuten keine Nichtverfügbarkeit. Stimmen und Dienste sind keine neuen Basismodelle. API-Routen und Zertifizierungen bleiben erhalten.

Angezeigt / gesamt: 482 / 613
Claude Haiku 5.5claude-haiku-5-5Eigenständiges ModellAnthropic · Produktiv2026-10-07Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung—Preis-Leistung—
Nicht bewertet
Eingabenutzung · pro Million Token200.000 PunkteCache-Treffernutzung · pro Million Token20.000 PunkteCache-Schreibnutzung · 5m · pro Million Token250.000 PunkteCache-Schreibnutzung · 1h · pro Million Token400.000 PunkteAusgabenutzung · pro Million Token1.000.000 PunkteWebsuche · pro 1.000 Sucheinheiten20.000.000 Punkte
Claude Haiku 5.5-100claude-haiku-5-5-100Eigenständiges ModellAnthropic · Produktiv2026-10-07Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated74.7Preis-Leistung · Estimated82.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basisNicht bewertet · 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.

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Gemini Nano Banana 2.1-100gemini-nano-banana-2.1Eigenständiges ModellGoogle · Produktiv2026-10-06Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung92.5Preis-Leistung · Estimated66.5
VorläufigNicht bewertet · Confidence 0%
Eingabenutzung · pro Million Token3.000.000 PunkteEingabenutzung · Bild · pro Million Token3.000.000 PunkteCache-Treffernutzung · pro Million Token300.000 PunkteAusgabenutzung · pro Million Token15.000.000 PunkteCache-Treffernutzung · Bild · pro Million Token300.000 PunkteAusgabenutzung · Bild · pro Million Token60.000.000 Punkte
Qwen-Image-2.1-Proqwen-image-2.1-proEigenständiges ModellQwen · Produktiv2026-10-02Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated66.4Preis-Leistung · Estimated61.5
Estimate basis2026-10-08 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 · Independent
Ausgabenutzung · Bild · pro Bild68.494 Punkte
Grok 4.7-100grok-4.7-100Eigenständiges ModellxAI · Vorschau2026-09-30Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung—Preis-Leistung—
Nicht bewertet
Eingabenutzung · pro Million Token4.000.000 PunkteCache-Treffernutzung · pro Million Token1.000.000 PunkteAusgabenutzung · pro Million Token12.000.000 Punkte
GPT-6.1 Solgpt-6.1-solEigenständiges ModellOpenAI · Produktiv2026-09-29Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated82.2Preis-Leistung · Estimated69.2
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token4.000.000 PunkteCache-Treffernutzung · pro Million Token200.000 PunkteCache-Schreibnutzung · pro Million Token5.000.000 PunkteAusgabenutzung · pro Million Token20.000.000 Punkte
Claude Sonnet 5.5claude-sonnet-5-5Eigenständiges ModellAnthropic · Produktiv2026-09-28Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated74.4Preis-Leistung · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token4.000.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteCache-Schreibnutzung · 5m · pro Million Token5.000.000 PunkteCache-Schreibnutzung · 1h · pro Million Token8.000.000 PunkteAusgabenutzung · pro Million Token20.000.000 PunkteWebsuche · pro 1.000 Sucheinheiten20.000.000 Punkte
Claude Sonnet 5.5-100claude-sonnet-5-5-100Eigenständiges ModellAnthropic · Produktiv2026-09-28Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated74.4Preis-Leistung · Estimated67.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

决策模型(预览版)decision-model-previewEigenständiges ModellQwen · Produktiv2026-09-24Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token0 Punkte
Gemini 3.8 Live-100gemini-3.8-liveEigenständiges ModellGoogle · Produktiv2026-09-24Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated76.9Preis-Leistung · Estimated68.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.500.000 PunkteVideoeingabe · pro Million Token2.000.000 PunkteEingabenutzung · Audio · pro Million Token6.000.000 PunkteAusgabenutzung · pro Million Token9.000.000 PunkteAusgabenutzung · Audio · pro Million Token24.000.000 PunkteAusgabenutzung · Videogenerierung · pro Million Token2.000.000 Punkte
Claude Opus 5.5claude-opus-5-5Eigenständiges ModellAnthropic · Produktiv2026-09-22Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated86.9Preis-Leistung · Estimated69.6
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token8.000.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteCache-Schreibnutzung · 5m · pro Million Token10.000.000 PunkteCache-Schreibnutzung · 1h · pro Million Token16.000.000 PunkteAusgabenutzung · pro Million Token40.000.000 PunkteWebsuche · pro 1.000 Sucheinheiten20.000.000 Punkte
Claude Opus 5.5-100claude-opus-5-5-100Eigenständiges ModellAnthropic · Produktiv2026-09-22Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated86.9Preis-Leistung · Estimated75.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT-6 Lunagpt-6-lunaEigenständiges ModellOpenAI · Produktiv2026-09-22Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated59.4Preis-Leistung · Estimated65.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token200.000 PunkteCache-Treffernutzung · pro Million Token20.000 PunkteCache-Schreibnutzung · pro Million Token250.000 PunkteAusgabenutzung · pro Million Token1.000.000 Punkte
GPT-6 Solgpt-6-solEigenständiges ModellOpenAI · Produktiv2026-09-22Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated74.3Preis-Leistung · Estimated63.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token4.000.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteCache-Schreibnutzung · pro Million Token5.000.000 PunkteAusgabenutzung · pro Million Token20.000.000 Punkte
Grok 4.7grok-4.7Eigenständiges ModellxAI · Produktiv2026-09-21Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung—Preis-Leistung—
Nicht bewertet
Eingabenutzung · pro Million Token4.000.000 PunkteCache-Treffernutzung · pro Million Token1.000.000 PunkteAusgabenutzung · pro Million Token12.000.000 Punkte
Qwen-Audio-3.1-Realtime-Plusqwen-audio-3.1-realtime-plusEigenständiges ModellQwen · Produktiv2026-09-20Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3.8-Livetranslate-Flash-Realtimeqwen3.8-livetranslate-flash-realtimeEigenständiges ModellQwen · Produktiv2026-09-18Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-MT-Uniqwen-mt-uniEigenständiges ModellQwen · Produktiv2026-09-16Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated49.4Preis-Leistung · Estimated49.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-kimi/kimi-k2.8-previewqwen-kimi-kimi-k2.8-previewEigenständiges ModellMoonshot AI · Produktiv2026-09-11Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.780.822 PunkteCache-Treffernutzung · pro Million Token465.753 PunkteAusgabenutzung · pro Million Token7.397.260 Punkte
DeepSeek V4.1 Flashdeepseek-flashEigenständiges ModellDeepSeek · Produktiv2026-09-10Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated78.1Preis-Leistung · Estimated77.6
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token300.000 PunkteCache-Treffernutzung · pro Million Token6.000 PunkteAusgabenutzung · pro Million Token1.200.000 Punkte
doubao-deepseek-v4-1-flashdoubao-deepseek-v4-1-flash-260910Fester Snapshot / Version · Einziger ZugangDeepSeek · Produktiv2026-09-10Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token273.973 PunkteCache-Treffernutzung · pro Million Token5.479 PunkteAusgabenutzung · pro Million Token1.095.890 Punkte
qwen-DeepSeek V4.1 Flashqwen-deepseek-v4.1-flashEigenständiges ModellDeepSeek · Produktiv2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated61.4Preis-Leistung · Estimated66.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token273.973 PunkteCache-Treffernutzung · pro Million Token27.397 PunkteAusgabenutzung · pro Million Token1.095.890 Punkte
qwen-vanchin/deepseek-v4.1-flashqwen-vanchin-deepseek-v4.1-flashEigenständiges ModellDeepSeek · Produktiv2026-09-10Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated61.4Preis-Leistung · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT Image 2.5 Flaregpt-image-2.5-flareEigenständiges ModellOpenAI · Produktiv2026-09-08Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung98.5Preis-Leistung70.3
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Eingabenutzung · pro Million Token10.000.000 PunkteCache-Treffernutzung · pro Million Token2.500.000 PunkteEingabenutzung · Bild · pro Million Token16.000.000 PunkteCache-Treffernutzung · Bild · pro Million Token4.000.000 PunkteAusgabenutzung · Bild · pro Million Token60.000.000 Punkte
GPT Image 2.5 Sunburstgpt-image-2.5-sunburstEigenständiges ModellOpenAI · Produktiv2026-09-08Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung100.0Preis-Leistung71.4
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Eingabenutzung · pro Million Token10.000.000 PunkteCache-Treffernutzung · pro Million Token2.500.000 PunkteEingabenutzung · Bild · pro Million Token16.000.000 PunkteCache-Treffernutzung · Bild · pro Million Token4.000.000 PunkteAusgabenutzung · Bild · pro Million Token60.000.000 Punkte
GPT-6 Astragpt-6-astraEigenständiges ModellOpenAI · Produktiv2026-09-03Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated85.4Preis-Leistung · Estimated64.8
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token20.000.000 PunkteCache-Treffernutzung · pro Million Token2.000.000 PunkteCache-Schreibnutzung · pro Million Token25.000.000 PunkteAusgabenutzung · pro Million Token100.000.000 Punkte
Gemini 3.8 Flash-100gemini-3.8-flash-100Eigenständiges ModellGoogle · Produktiv2026-09-02Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung—Preis-Leistung—
Nicht bewertet
Eingabenutzung · pro Million Token3.000.000 PunkteEingabenutzung · Bild · pro Million Token3.000.000 PunkteEingabenutzung · Audio · pro Million Token3.000.000 PunkteVideoeingabe · pro Million Token3.000.000 PunkteCache-Treffernutzung · pro Million Token300.000 PunkteAusgabenutzung · pro Million Token15.000.000 PunkteCache-Schreibnutzung · pro Million Token3.000.000 PunkteExpliziter Cache-Speicher · je Million Token-Stunden2.000.000 Punkte
Claude Fable 5.1claude-fable-5-1Eigenständiges ModellAnthropic · Produktiv2026-09-01Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated89.2Preis-Leistung · 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 estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token20.000.000 PunkteCache-Treffernutzung · pro Million Token500.000 PunkteCache-Schreibnutzung · 5m · pro Million Token25.000.000 PunkteCache-Schreibnutzung · 1h · pro Million Token40.000.000 PunkteAusgabenutzung · pro Million Token100.000.000 PunkteWebsuche · pro 1.000 Sucheinheiten20.000.000 Punkte
Claude Fable 5.1-100claude-fable-5-1-100Eigenständiges ModellAnthropic · Produktiv2026-09-01Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated89.2Preis-Leistung—
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 estimates
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Doubao-Seed-2.1-Litedoubao-seed-2-1-lite-260915Fester Snapshot / Version · Einziger ZugangDoubao · Produktiv2026-09 (offiziell nur der Monat)Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated63.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token43.836 PunkteAusgabenutzung · pro Million Token739.726 Punkte
doubao-seedream-5-0-flashdoubao-seedream-5-0-flash-260915Fester Snapshot / Version · Einziger ZugangDoubao · Produktiv2026-09 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated65.8Preis-Leistung · Estimated61.1
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

千问3.7-通用文本向量-flashqwen3.7-text-embedding-flashEigenständiges ModellAlibaba Cloud · Produktiv2026-09-01Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.3Preis-Leistung · Estimated73.6
Estimate basis2026-10-08 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 · Official
Embedding-Eingabe · pro Million Token34.247 Punkte
千问3.7-通用文本重排序qwen3.7-text-rerankEigenständiges ModellAlibaba Cloud · Produktiv2026-09-01Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated72.5Preis-Leistung · Estimated80.8
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token136.987 Punkte
Qwen3.8-Omni-Flashqwen3.8-omni-flashEigenständiges ModellQwen · Produktiv2026-09 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated61.4Preis-Leistung · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3.8-Omni-Flash-Realtimeqwen3.8-omni-flash-realtimeEigenständiges ModellQwen · Produktiv2026-09 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-MT-Image-2.0qwen-mt-image-2.0Eigenständiges ModellQwen · Produktiv2026-08-28Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated73.8Preis-Leistung · Estimated66.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Cohere Parse v5cohere-parse-v5Eigenständiges ModellCohere · Vorschau2026-08-27Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung79.2Preis-Leistung85.4
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 18%cohere-parsebench · Official
Dokumentverarbeitung · pro 1.000 Seiten3.000.000 Punkte
Gemini Omni 1.1 Flash Preview-100gemini-omni-1.1-flash-previewEigenständiges ModellGoogle · Produktiv2026-08-27Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated49.9Preis-Leistung · Estimated49.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ZHIPU/GLM-5.3-Flashqwen-zhipu-glm-5.3-flashEigenständiges ModellZhipu AI · Produktiv2026-08-26Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated48.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token63.014 PunkteAusgabenutzung · pro Million Token767.123 Punkte
Qwen3.8-Flashqwen3.8-flashEigenständiges ModellQwen · Produktiv2026-08-25Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated61.4Preis-Leistung · Estimated67.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token27.397 PunkteAusgabenutzung · pro Million Token739.726 Punkte
qwen-Kimi-K3qwen-kimi-k3Eigenständiges ModellMoonshot · Produktiv2026-08-19Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated39.7Preis-Leistung · Estimated38.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token5.479.452 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token27.397.260 Punkte
Qwen3.8-27Bqwen3.8-27bEigenständiges ModellQwen · Produktiv2026-08-17Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated65.0Preis-Leistung · Estimated64.2
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token821.918 PunkteCache-Treffernutzung · pro Million Token164.384 PunkteAusgabenutzung · pro Million Token3.287.671 Punkte
qwen-GLM-5.3qwen-glm-5.3Eigenständiges ModellZhipu AI · Produktiv2026-08-14Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated61.1Preis-Leistung · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
qwen-ZHIPU/GLM-5.3qwen-zhipu-glm-5.3Eigenständiges ModellZhipu AI · Produktiv2026-08-14Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
DeepSeek V4 Prodeepseek-v4-proEigenständiges ModellDeepSeek · Produktiv2026-08-13Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated64.4Preis-Leistung · Estimated62.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.320.000 PunkteCache-Treffernutzung · pro Million Token44.000 PunkteAusgabenutzung · pro Million Token3.960.000 Punkte
GLM-5.3glm-5.3Eigenständiges ModellZhipu · Produktiv2026-08-13Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated71.7Preis-Leistung · Estimated65.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
GLM-5.3-Flashglm-5.3-flashEigenständiges ModellZhipu · Produktiv2026-08-13Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated65.1Preis-Leistung · Estimated70.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token63.014 PunkteAusgabenutzung · pro Million Token767.123 Punkte
Grok 4.6grok-4.6Eigenständiges ModellxAI · Vorschau2026-08-12Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated70.4Preis-Leistung · 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 estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token8.000.000 PunkteCache-Treffernutzung · pro Million Token2.000.000 PunkteAusgabenutzung · pro Million Token24.000.000 Punkte
Grok 4.6-100grok-4.6-100Eigenständiges ModellxAI · Produktiv2026-08-12Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated70.4Preis-Leistung—
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 estimates
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

MAI Thinking 1mai-thinking-1Eigenständiges ModellMicrosoft AI · Vorschau2026-08-12Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated51.7
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token4.000.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteAusgabenutzung · pro Million Token16.000.000 Punkte
Qwen3.8-2.4T-A95Bqwen3.8-2.4t-a95bEigenständiges ModellQwen · Produktiv2026-08-12Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated65.0Preis-Leistung · Estimated58.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token3.287.671 PunkteCache-Treffernutzung · pro Million Token410.959 PunkteAusgabenutzung · pro Million Token9.863.014 Punkte
万相3.0-视频生成wan3.0-videoEigenständiges ModellAlibaba Cloud · Produktiv2026-08-06Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated92.6Preis-Leistung · Estimated72.9
Estimate basis2026-10-08 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 · Independent
Videogenerierung 480P · pro Sekunde57.535 PunkteVideogenerierung 720P · pro Sekunde115.069 PunkteVideogenerierung 1080P · pro Sekunde230.137 Punkte
Qwen3.8-Maxqwen3.8-maxEigenständiges ModellQwen · Produktiv2026-08-02Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated76.0Preis-Leistung · Estimated66.6
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token3.287.671 PunkteCache-Treffernutzung · pro Million Token410.959 PunkteAusgabenutzung · pro Million Token9.863.014 Punkte
Gemini 3.5 Transcribe Live Preview-100gemini-3.5-transcribe-live-previewEigenständiges ModellGoogle · Produktiv2026-08 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Gemini 3.5 Transcribe Preview-100gemini-3.5-transcribe-previewEigenständiges ModellGoogle · Produktiv2026-08 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

doubao-DeepSeek V4 Flash GA (2026-07-31)doubao-deepseek-v4-flash-ga-260731Fester Snapshot / Version · Einziger ZugangDeepSeek · Produktiv2026-07-31Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated58.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token821.918 PunkteCache-Treffernutzung · pro Million Token27.397 PunkteAusgabenutzung · pro Million Token2.465.753 Punkte
qwen-MiniMax/MiniMax-H3qwen-minimax-minimax-h3Eigenständiges Modellmini-max · Produktiv2026-07-31Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Audio-3.0-ASR-Flashqwen-audio-3.0-asr-flashEigenständiges ModellAlibaba Cloud · Produktiv2026-07-30Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.4Preis-Leistung · Estimated94.0
Estimate basis2026-10-08 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 · Independent
Transkription · pro Sekunde61 Punkte
qwen-audio-3.0-asr-flash-filetransqwen-audio-3.0-asr-flash-filetransEigenständiges ModellQwen · Produktiv2026-07-30Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Audio-3.0-ASR-Flash-Streamingqwen-audio-3.0-asr-flash-streamingEigenständiges ModellQwen · Produktiv2026-07-30Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT Live Transcribegpt-live-transcribeEigenständiges ModellOpenAI · Produktiv2026-07-28Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.4Preis-Leistung · Estimated64.0
Estimate basis2026-10-08 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 · Independent
Transkription · pro Stunde2.040.000 Punkte
GPT Transcribegpt-transcribeEigenständiges ModellOpenAI · Produktiv2026-07-28Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.4Preis-Leistung · Estimated81.7
Estimate basis2026-10-08 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 · Independent
Transkription · pro Stunde540.000 Punkte
qwen-PixVerse-V6-r2v-omniqwen-pixverse-pixverse-v6-r2v-omniEigenständiges Modellpixverse · Produktiv2026-07-26Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated61.1Preis-Leistung · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Claude Opus 5claude-opus-5Eigenständiges ModellAnthropic · Produktiv2026-07-24Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated81.9Preis-Leistung · 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 estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token10.000.000 PunkteCache-Treffernutzung · pro Million Token1.000.000 PunkteCache-Schreibnutzung · 5m · pro Million Token12.500.000 PunkteCache-Schreibnutzung · 1h · pro Million Token20.000.000 PunkteAusgabenutzung · pro Million Token50.000.000 Punkte
Claude Opus 5-100claude-opus-5-100Eigenständiges ModellAnthropic · Produktiv2026-07-24Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated81.9Preis-Leistung—
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 estimates
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Gemini 3.5 Flash-Lite-100gemini-3.5-flash-lite-100Eigenständiges ModellGoogle · Produktiv2026-07-21Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated52.3Preis-Leistung · Estimated55.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token600.000 PunkteCache-Treffernutzung · pro Million Token60.000 PunkteAusgabenutzung · pro Million Token5.000.000 Punkte
Qwen3.7-Flashqwen3.7-flashEigenständiges ModellQwen · Produktiv2026-07-21Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated61.4Preis-Leistung · Estimated73.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 32.000 TokenEingabenutzung · pro Million Token54.795 PunkteCache-Treffernutzung · pro Million Token10.959 PunkteAusgabenutzung · pro Million Token219.178 Punkte
Input 32.001 – 256.000 TokenEingabenutzung · pro Million Token164.384 PunkteCache-Treffernutzung · pro Million Token32.877 PunkteAusgabenutzung · pro Million Token657.534 Punkte
Input 256.001+ TokenEingabenutzung · pro Million Token328.767 PunkteCache-Treffernutzung · pro Million Token65.753 PunkteAusgabenutzung · pro Million Token1.315.068 Punkte
Qwen-Image-3.0qwen-image-3.0Eigenständiges ModellAlibaba Cloud · Produktiv2026-07-21Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated73.8Preis-Leistung · Estimated81.7
Estimate basis2026-10-08 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 · Independent
Bild Eingabenutzung 1K · pro Bild5.480 PunkteBild Eingabenutzung 2K · pro Bild5.480 PunkteBild Ausgabenutzung 1K · pro Bild49.316 PunkteBild Ausgabenutzung 2K · pro Bild49.316 Punkte
Kimi K3kimi-k3Eigenständiges ModellMoonshot · Produktiv2026-07-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated80.1Preis-Leistung · Estimated66.4
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token5.479.452 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token27.397.260 Punkte
qwen-kimi/kimi-k3qwen-kimi-kimi-k3Eigenständiges ModellMoonshot AI · Produktiv2026-07-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token5.479.452 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token27.397.260 Punkte
Qwen3.7-通用文本向量qwen3.7-text-embeddingEigenständiges ModellAlibaba Cloud · Produktiv2026-07-15Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.3Preis-Leistung · Estimated53.1
Estimate basis2026-10-08 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 · Official
Embedding-Eingabe · pro Million Token136.987 Punkte
Qwen-Audio-3.0-Realtime-Flashqwen-audio-3.0-realtime-flashEigenständiges ModellQwen · Produktiv2026-07-14Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Audio-3.0-Realtime-Plusqwen-audio-3.0-realtime-plusEigenständiges ModellQwen · Produktiv2026-07-14Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT-5.6 Lunagpt-5.6-lunaEigenständiges ModellOpenAI · Produktiv2026-07-09Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated63.7Preis-Leistung · Estimated65.5
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token400.000 PunkteCache-Treffernutzung · pro Million Token40.000 PunkteCache-Schreibnutzung · pro Million Token500.000 PunkteAusgabenutzung · pro Million Token2.400.000 Punkte
GPT-5.6 Solgpt-5.6-solEigenständiges ModellOpenAI · Produktiv2026-07-09Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated83.1Preis-Leistung · Estimated67.0
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token8.000.000 PunkteCache-Treffernutzung · pro Million Token800.000 PunkteCache-Schreibnutzung · pro Million Token10.000.000 PunkteAusgabenutzung · pro Million Token40.000.000 Punkte
GPT-5.6 Terragpt-5.6-terraEigenständiges ModellOpenAI · Produktiv2026-07-09Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated73.1Preis-Leistung · Estimated62.5
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token4.000.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteCache-Schreibnutzung · pro Million Token5.000.000 PunkteAusgabenutzung · pro Million Token24.000.000 Punkte
gpt-live-1gpt-live-1Eigenständiges ModellOpenAI · Produktiv2026-07-08Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated48.3Preis-Leistung · Estimated48.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT Realtime 2.1gpt-realtime-2.1Eigenständiges ModellOpenAI · Vorschau2026-07-06Echtzeit-Sprache und Text verfügbar. Bildeingabe und Tool-Ausführung im Gespräch sind nicht aktiviert.Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated45.3Preis-Leistung · Estimated31.7
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token8.000.000 PunkteCache-Treffernutzung · pro Million Token800.000 PunkteAusgabenutzung · pro Million Token48.000.000 PunkteEingabenutzung · Bild · pro Million Token10.000.000 PunkteCache-Treffernutzung · Bild · pro Million Token1.000.000 PunkteEingabenutzung · Audio · pro Million Token64.000.000 PunkteCache-Treffernutzung · Audio · pro Million Token800.000 PunkteAusgabenutzung · Audio · pro Million Token128.000.000 Punkte
GPT Realtime 2.1 Minigpt-realtime-2.1-miniEigenständiges ModellOpenAI · Vorschau2026-07-06Echtzeit-Sprache und Text verfügbar. Bildeingabe und Tool-Ausführung im Gespräch sind nicht aktiviert.Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated45.3Preis-Leistung · Estimated61.7
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token1.200.000 PunkteCache-Treffernutzung · pro Million Token120.000 PunkteAusgabenutzung · pro Million Token4.800.000 PunkteEingabenutzung · Bild · pro Million Token1.600.000 PunkteCache-Treffernutzung · Bild · pro Million Token160.000 PunkteEingabenutzung · Audio · pro Million Token20.000.000 PunkteCache-Treffernutzung · Audio · pro Million Token600.000 PunkteAusgabenutzung · Audio · pro Million Token40.000.000 Punkte
Qwen-Audio-3.0-TTS-Flashqwen-audio-3.0-tts-flashEigenständiges ModellAlibaba Cloud · Produktiv2026-07 (offiziell nur der Monat)Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated74.4Preis-Leistung · Estimated74.8
Estimate basis2026-10-08 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 · Official
Audio · pro 10.000 Zeichen273.973 Punkte
Qwen-Audio-3.0-TTS-Plusqwen-audio-3.0-tts-plusEigenständiges ModellAlibaba Cloud · Produktiv2026-07 (offiziell nur der Monat)Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated74.4Preis-Leistung · Estimated63.8
Estimate basis2026-10-08 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 · Official
Audio · pro 10.000 Zeichen383.562 Punkte
claude-sonnet-5claude-sonnet-5Eigenständiges ModellAnthropic · Produktiv2026-06-30Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated70.2Preis-Leistung · Estimated64.1
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

claude-sonnet-5-100claude-sonnet-5-100Eigenständiges ModellAnthropic · Produktiv2026-06-30Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated70.2Preis-Leistung · Estimated64.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Doubao Seed 2.1 Turbo (2026-06-28)doubao-seed-2-1-turbo-260628Fester Snapshot / Version · Einziger ZugangByteDance · Produktiv2026-06-28Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated57.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token821.918 PunkteCache-Treffernutzung · pro Million Token164.384 PunkteAusgabenutzung · pro Million Token4.109.589 Punkte
Mistral OCR 4mistral-ocr-4-0Eigenständiges ModellMistral AI · Vorschau2026-06-23Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung81.8Preis-Leistung57.3
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 25%mistral-ocr · Officialcohere-parsebench · Official
Dokumentverarbeitung · pro 1.000 Seiten8.000.000 PunkteDokumentverarbeitung mit strukturierten Annotationen · pro 1.000 Seiten10.000.000 Punkte
HappyHorse-1.1-I2Vhappyhorse-1.1-i2vEigenständiges ModellAlibaba Cloud · Produktiv2026-06-22Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated80.9Preis-Leistung · Estimated56.6
Estimate basis2026-10-08 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 · Independent
Videogenerierung 480P · pro Sekunde123.288 PunkteVideogenerierung 720P · pro Sekunde246.576 PunkteVideogenerierung 1080P · pro Sekunde328.768 Punkte
HappyHorse-1.1-R2Vhappyhorse-1.1-r2vEigenständiges ModellAlibaba Cloud · Produktiv2026-06-22Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated80.9Preis-Leistung · Estimated56.6
Estimate basis2026-10-08 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 · Independent
Videogenerierung 480P · pro Sekunde123.288 PunkteVideogenerierung 720P · pro Sekunde246.576 PunkteVideogenerierung 1080P · pro Sekunde328.768 Punkte
HappyHorse-1.1-T2Vhappyhorse-1.1-t2vEigenständiges ModellAlibaba Cloud · Produktiv2026-06-22Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated80.9Preis-Leistung · Estimated56.6
Estimate basis2026-10-08 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 · Independent
Videogenerierung 480P · pro Sekunde123.288 PunkteVideogenerierung 720P · pro Sekunde246.576 PunkteVideogenerierung 1080P · pro Sekunde328.768 Punkte
doubao-GLM 5.2 (2026-06-17)doubao-glm-5-2-260617Fester Snapshot / Version · Einziger ZugangZhipu · Produktiv2026-06-17Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated54.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
qwen-HappyOyster-1.0-Adventureqwen-happyoyster-1.0-adventureEigenständiges Modellhappyoyster · Produktiv2026-06-17Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated43.2Preis-Leistung · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GLM-5.2glm-5.2Eigenständiges ModellZhipu · Produktiv2026-06-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated66.4Preis-Leistung · Estimated61.3
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
Qwen3.5-OCRqwen3.5-ocrEigenständiges ModellAlibaba Cloud · Produktiv2026-06-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated81.8Preis-Leistung · Estimated72.3
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token136.987 PunkteAusgabenutzung · pro Million Token547.946 Punkte
qwen-GLM-5.2qwen-glm-5.2Eigenständiges ModellZhipu · Produktiv2026-06-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated61.1Preis-Leistung · Estimated57.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
qwen-pixverse/pixverse-upscaleqwen-pixverse-pixverse-upscaleEigenständiges Modellpixverse · Produktiv2026-06-16Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ZHIPU/GLM-5.2qwen-zhipu-glm-5.2Eigenständiges ModellZhipu AI · Produktiv2026-06-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
qwen-kimi-k2.7-codeqwen-kimi-k2.7-codeEigenständiges ModellMoonshot · Produktiv2026-06-15Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated34.7Preis-Leistung · Estimated39.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.780.822 PunkteCache-Treffernutzung · pro Million Token356.164 PunkteAusgabenutzung · pro Million Token7.397.260 Punkte
Kimi K2.7 Codekimi-k2.7-codeEigenständiges ModellMoonshot · Produktiv2026-06-12Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated46.3Preis-Leistung · Estimated47.8
8/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.780.822 PunkteCache-Treffernutzung · pro Million Token356.164 PunkteAusgabenutzung · pro Million Token7.397.260 Punkte
qwen-kimi/kimi-k2.7-codeqwen-kimi-kimi-k2.7-codeEigenständiges ModellMoonshot AI · Produktiv2026-06-12Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated29.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.780.822 PunkteCache-Treffernutzung · pro Million Token356.164 PunkteAusgabenutzung · pro Million Token7.397.260 Punkte
claude-fable-5claude-fable-5Eigenständiges ModellAnthropic · Produktiv2026-06-09Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated87.7Preis-Leistung · Estimated76.4
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

claude-fable-5-100claude-fable-5-100Eigenständiges ModellAnthropic · Produktiv2026-06-09Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated87.7Preis-Leistung · Estimated76.4
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3.7-Max-2026-06-08qwen3.7-max-2026-06-08Fester Snapshot / Version · Einziger ZugangQwen · Produktiv2026-06-09Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated64.5Preis-Leistung · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token3.287.671 PunkteCache-Treffernutzung · pro Million Token657.534 PunkteAusgabenutzung · pro Million Token9.863.014 Punkte
doubao-seedance-2-5-260628doubao-seedance-2-5-260628Fester Snapshot / Version · Einziger ZugangByteDance · Produktiv2026-06 (offiziell nur der Monat)Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated90.4Preis-Leistung · Estimated63.3
Version comparison review
Estimate basis2026-10-08 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 · Independent
Ausgabenutzung · Videogenerierung · pro Million Token19.178.083 Punkte
doubao-seed-evolvingdoubao-seed-evolvingAlias · Einziger ZugangDoubao · Produktiv2026-06 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

doubao-seedream-5-0-pro-260628doubao-seedream-5-0-pro-260628Fester Snapshot / Version · Einziger ZugangByteDance · Produktiv2026-06 (offiziell nur der Monat)Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated85.2Preis-Leistung · Estimated69.2
Estimate basis2026-10-08 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 · Independent
Ausgabenutzung · Bild · pro Bild82.192 PunkteEingabenutzung · Bild · pro Bild5.480 Punkte
Fun-ASR-Flash-2026-06-15fun-asr-flash-2026-06-15Fester Snapshot / Version · Einziger ZugangAlibaba Cloud · Produktiv2026-06 (offiziell nur der Monat)Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.4Preis-Leistung · Estimated94.0
Estimate basis2026-10-08 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 · Independent
Transkription · pro Sekunde61 Punkte
Qwen3.7-Plusqwen3.7-plusEigenständiges ModellQwen · Produktiv2026-06-01Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.0Preis-Leistung · Estimated60.5
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 256.000 TokenEingabenutzung · pro Million Token438.356 PunkteCache-Treffernutzung · pro Million Token87.671 PunkteAusgabenutzung · pro Million Token1.753.425 Punkte
Input 256.001+ TokenEingabenutzung · pro Million Token1.315.068 PunkteCache-Treffernutzung · pro Million Token263.014 PunkteAusgabenutzung · pro Million Token5.260.274 Punkte
qwen-MiniMax/MiniMax-M3qwen-minimax-minimax-m3Eigenständiges Modellmini-max · Produktiv2026-06-01Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated46.0
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.150.685 PunkteCache-Treffernutzung · pro Million Token230.137 PunkteAusgabenutzung · pro Million Token4.602.740 Punkte
qwen-stepfun/step-3.7-flashqwen-stepfun-step-3.7-flashEigenständiges Modellstepfun · Produktiv2026-05-29Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated61.4Preis-Leistung · Estimated64.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token369.863 PunkteCache-Treffernutzung · pro Million Token73.973 PunkteAusgabenutzung · pro Million Token2.219.178 Punkte
claude-opus-4-8claude-opus-4-8Eigenständiges ModellAnthropic · Produktiv2026-05-28Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated74.3Preis-Leistung · Estimated67.0
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

claude-opus-4-8-100claude-opus-4-8-100Eigenständiges ModellAnthropic · Produktiv2026-05-28Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated74.3Preis-Leistung · Estimated67.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3.7-Maxqwen3.7-maxEigenständiges ModellQwen · Produktiv2026-05-21Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated64.5Preis-Leistung · Estimated58.6
8/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token3.287.671 PunkteCache-Treffernutzung · pro Million Token657.534 PunkteAusgabenutzung · pro Million Token9.863.014 Punkte
Cohere Command A Pluscohere-command-a-plus-05-2026Eigenständiges ModellCohere · Vorschau2026-05-20Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated55.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.600.000 PunkteAusgabenutzung · pro Million Token6.400.000 Punkte
Qwen3.7-Max-Previewqwen3.7-max-previewEigenständiges ModellQwen · Vorschau2026-05-20Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated64.5Preis-Leistung · Estimated58.6
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token3.287.671 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token9.863.014 Punkte
Qwen3.5-LiveTranslate-Flash-Realtimeqwen3.5-livetranslate-flash-realtimeEigenständiges ModellQwen · Produktiv2026-05-19Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Grok 4.3grok-4.3Eigenständiges ModellxAI · Vorschau2026-05-12Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated44.8Preis-Leistung · 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 estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.500.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteAusgabenutzung · pro Million Token5.000.000 Punkte
Mistral Medium 3.5mistral-medium-3-5Eigenständiges ModellMistral AI · Vorschau2026-04-28Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated60.6Preis-Leistung · Estimated55.3
6/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token3.000.000 PunkteAusgabenutzung · pro Million Token15.000.000 Punkte
HappyHorse-1.0-I2Vhappyhorse-1.0-i2vEigenständiges ModellAlibaba Cloud · Produktiv2026-04-27Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated80.9Preis-Leistung · Estimated56.6
Estimate basis2026-10-08 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 · Independent
Videogenerierung 720P · pro Sekunde246.576 PunkteVideogenerierung 1080P · pro Sekunde438.357 Punkte
HappyHorse-1.0-R2Vhappyhorse-1.0-r2vEigenständiges ModellAlibaba Cloud · Produktiv2026-04-27Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated80.9Preis-Leistung · Estimated56.6
Estimate basis2026-10-08 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 · Independent
Videogenerierung 720P · pro Sekunde246.576 PunkteVideogenerierung 1080P · pro Sekunde438.357 Punkte
HappyHorse-1.0-T2Vhappyhorse-1.0-t2vEigenständiges ModellAlibaba Cloud · Produktiv2026-04-27Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated80.9Preis-Leistung · Estimated56.6
Estimate basis2026-10-08 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 · Independent
Videogenerierung 720P · pro Sekunde246.576 PunkteVideogenerierung 1080P · pro Sekunde438.357 Punkte
qwen-DeepSeek-V4-Proqwen-deepseek-v4-proEigenständiges ModellDeepSeek · Produktiv2026-04-24Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated70.1Preis-Leistung · Estimated63.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token3.287.671 PunkteCache-Treffernutzung · pro Million Token273.973 PunkteAusgabenutzung · pro Million Token6.575.342 Punkte
GPT-5.5gpt-5.5Eigenständiges ModellOpenAI · Produktiv2026-04-23Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated80.5Preis-Leistung · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token10.000.000 PunkteCache-Treffernutzung · pro Million Token1.000.000 PunkteAusgabenutzung · pro Million Token60.000.000 Punkte
qwen-xiaomi/mimo-v2.5-proqwen-xiaomi-mimo-v2.5-proEigenständiges ModellXiaomi · Produktiv2026-04-23Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated30.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.917.808 PunkteCache-Treffernutzung · pro Million Token383.562 PunkteAusgabenutzung · pro Million Token5.753.425 Punkte
Qwen3.6-27Bqwen3.6-27bEigenständiges ModellQwen · Produktiv2026-04-22Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated46.6Preis-Leistung · Estimated50.5
7/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token821.918 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token4.931.507 Punkte
GPT Image 2gpt-image-2Eigenständiges ModellOpenAI · Produktiv2026-04-21Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung97.0Preis-Leistung69.3
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Eingabenutzung · pro Million Token10.000.000 PunkteCache-Treffernutzung · pro Million Token2.500.000 PunkteEingabenutzung · Bild · pro Million Token16.000.000 PunkteCache-Treffernutzung · Bild · pro Million Token4.000.000 PunkteAusgabenutzung · Bild · pro Million Token60.000.000 Punkte
qwen-Kimi-K2.6qwen-kimi-k2.6Eigenständiges ModellMoonshot · Produktiv2026-04-21Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated34.9Preis-Leistung · Estimated39.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.780.822 PunkteCache-Treffernutzung · pro Million Token356.164 PunkteAusgabenutzung · pro Million Token7.397.260 Punkte
Kimi K2.6kimi-k2.6Eigenständiges ModellMoonshot · Produktiv2026-04-20Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated77.4Preis-Leistung · Estimated69.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.780.822 PunkteCache-Treffernutzung · pro Million Token301.370 PunkteAusgabenutzung · pro Million Token7.397.260 Punkte
qwen-Kimi/Kimi K2.6qwen-kimi-kimi-k2.6Eigenständiges ModellMoonshot AI · Produktiv2026-04-20Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.780.822 PunkteCache-Treffernutzung · pro Million Token301.370 PunkteAusgabenutzung · pro Million Token7.397.260 Punkte
claude-opus-4-7claude-opus-4-7Eigenständiges ModellAnthropic · Produktiv2026-04-16Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated74.1Preis-Leistung · Estimated66.9
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

claude-opus-4-7-100claude-opus-4-7-100Eigenständiges ModellAnthropic · Produktiv2026-04-16Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated74.1Preis-Leistung · Estimated66.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3.6-35B-A3Bqwen3.6-35b-a3bEigenständiges ModellQwen · Produktiv2026-04-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated45.4Preis-Leistung · Estimated51.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token493.151 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token2.958.904 Punkte
Qwen3.6-Flashqwen3.6-flashEigenständiges ModellQwen · Produktiv2026-04-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated58.2Preis-Leistung · Estimated62.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 256.000 TokenEingabenutzung · pro Million Token328.767 PunkteCache-Treffernutzung · pro Million Token65.753 PunkteAusgabenutzung · pro Million Token1.972.603 Punkte
Input 256.001+ TokenEingabenutzung · pro Million Token1.315.068 PunkteCache-Treffernutzung · pro Million Token263.014 PunkteAusgabenutzung · pro Million Token7.890.411 Punkte
qwen-GLM-5.1qwen-glm-5.1Eigenständiges ModellZhipu · Produktiv2026-04-14Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated61.1Preis-Leistung · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 32.000 TokenEingabenutzung · pro Million Token1.643.836 PunkteCache-Treffernutzung · pro Million Token328.767 PunkteAusgabenutzung · pro Million Token6.575.342 Punkte
Input 32.001+ TokenEingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token438.356 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
qwen-ViduQ3-mix_reference2videoqwen-vidu-viduq3-mix_reference2videoEigenständiges Modellvidu · Produktiv2026-04-13Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3_reference2videoqwen-vidu-viduq3_reference2videoEigenständiges Modellvidu · Produktiv2026-04-13Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-Turbo_reference2videoqwen-vidu-viduq3-turbo_reference2videoEigenständiges Modellvidu · Produktiv2026-04-13Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-PixVerse-C1-it2vqwen-pixverse-pixverse-c1-it2vEigenständiges Modellpixverse · Produktiv2026-04-07Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-PixVerse-C1-kf2vqwen-pixverse-pixverse-c1-kf2vEigenständiges Modellpixverse · Produktiv2026-04-07Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-PixVerse-C1-r2vqwen-pixverse-pixverse-c1-r2vEigenständiges Modellpixverse · Produktiv2026-04-07Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-PixVerse-C1-t2vqwen-pixverse-pixverse-c1-t2vEigenständiges Modellpixverse · Produktiv2026-04-07Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ZHIPU/GLM-5.1qwen-zhipu-glm-5.1Eigenständiges ModellZhipu AI · Produktiv2026-04-07Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
Wan2.7-I2Vwan2.7-i2vEigenständiges ModellAlibaba Cloud · Produktiv2026-04-07Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung78.7Preis-Leistung63.2
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Videogenerierung 720P · pro Sekunde164.384 PunkteVideogenerierung 1080P · pro Sekunde273.973 Punkte
Wan2.7-R2Vwan2.7-r2vEigenständiges ModellAlibaba Cloud · Produktiv2026-04-07Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated69.2Preis-Leistung · Estimated56.5
Estimate basis2026-10-08 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 · Independent
Videogenerierung 720P · pro Sekunde164.384 PunkteVideogenerierung 1080P · pro Sekunde273.973 Punkte
Wan2.7-T2Vwan2.7-t2vEigenständiges ModellAlibaba Cloud · Produktiv2026-04-07Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung59.6Preis-Leistung49.8
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Videogenerierung 720P · pro Sekunde164.384 PunkteVideogenerierung 1080P · pro Sekunde273.973 Punkte
qwen-Wan2.7-VideoEditwan2.7-videoeditEigenständiges ModellWan · Produktiv2026-04-07Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated69.2Preis-Leistung · Estimated63.4
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Grok 4.20 Non-Reasoninggrok-4-20-non-reasoningEigenständiges ModellxAI · Vorschau2026-04-06Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · 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 estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.500.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteAusgabenutzung · pro Million Token5.000.000 Punkte
Grok 4.20 Reasoninggrok-4-20-reasoningEigenständiges ModellxAI · Vorschau2026-04-06Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · 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 estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.500.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteAusgabenutzung · pro Million Token5.000.000 Punkte
Gemma 4 26B A4B It-100gemma-4-26b-a4b-it-maas-001Eigenständiges ModellGoogle · Vorschau2026-04-02Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated62.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token300.000 PunkteCache-Treffernutzung · pro Million Token30.000 PunkteAusgabenutzung · pro Million Token1.200.000 Punkte
Veo 3.1 Lite Generate 001-100veo-3.1-lite-generate-001Eigenständiges ModellGoogle · Produktiv2026-04-02Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

doubao-seed3d-2-0-260328doubao-seed3d-2-0-260328Fester Snapshot / Version · Einziger ZugangByteDance · Produktiv2026-04 (offiziell nur der Monat)Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung82.2Preis-Leistung57.5
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 18%seed3d-public · Official
Ausgabenutzung · 3D · pro Million Token21.917.809 Punkte
Qwen3.6-Plusqwen3.6-plusEigenständiges ModellQwen · Produktiv2026-04-01Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated54.5Preis-Leistung · Estimated57.7
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 256.000 TokenEingabenutzung · pro Million Token547.945 PunkteCache-Treffernutzung · pro Million Token109.589 PunkteAusgabenutzung · pro Million Token3.287.671 Punkte
Input 256.001+ TokenEingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token438.356 PunkteAusgabenutzung · pro Million Token13.150.685 Punkte
Wan2.7-Imagewan2.7-imageEigenständiges ModellAlibaba Cloud · Produktiv2026-04-01Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung41.7Preis-Leistung46.3
Version comparison review
Vorläufig2026-10-08 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 · Independent
Ausgabenutzung · Bild · pro Bild54.795 Punkte
Wan2.7-Image-Prowan2.7-image-proEigenständiges ModellAlibaba Cloud · Produktiv2026-04-01Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung44.1Preis-Leistung30.9
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Ausgabenutzung · Bild · pro Bild136.987 Punkte
qwen-PixVerse-V6-it2vqwen-pixverse-pixverse-v6-it2vEigenständiges Modellpixverse · Produktiv2026-03-29Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-PixVerse-V6-kf2vqwen-pixverse-pixverse-v6-kf2vEigenständiges Modellpixverse · Produktiv2026-03-29Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-PixVerse-V6-t2vqwen-pixverse-pixverse-v6-t2vEigenständiges Modellpixverse · Produktiv2026-03-29Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GLM-5.1glm-5.1Eigenständiges ModellZhipu · Produktiv2026-03-27Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated65.1Preis-Leistung · Estimated61.4
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 31.999 TokenEingabenutzung · pro Million Token1.643.836 PunkteCache-Treffernutzung · pro Million Token356.164 PunkteAusgabenutzung · pro Million Token6.575.342 Punkte
Input 32.000+ TokenEingabenutzung · pro Million Token2.191.781 PunkteCache-Treffernutzung · pro Million Token547.945 PunkteAusgabenutzung · pro Million Token7.671.233 Punkte
Lyria 3 Clip Preview-100lyria-3-clip-previewEigenständiges ModellGoogle · Produktiv2026-03-25Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Lyria 3 Pro Preview-100lyria-3-pro-previewEigenständiges ModellGoogle · Produktiv2026-03-25Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-MiniMax/MiniMax-M2.7qwen-minimax-minimax-m2.7Eigenständiges ModellMiniMax · Produktiv2026-03-18Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token575.342 PunkteCache-Treffernutzung · pro Million Token115.068 PunkteAusgabenutzung · pro Million Token2.301.370 Punkte
GPT-5.4 Minigpt-5.4-miniEigenständiges ModellOpenAI · Produktiv2026-03-17Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated47.9Preis-Leistung · Estimated48.9
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.500.000 PunkteCache-Treffernutzung · pro Million Token150.000 PunkteAusgabenutzung · pro Million Token9.000.000 Punkte
GPT-5.4 Nanogpt-5.4-nanoEigenständiges ModellOpenAI · Produktiv2026-03-17Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated48.6Preis-Leistung · Estimated54.8
11/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token400.000 PunkteCache-Treffernutzung · pro Million Token40.000 PunkteAusgabenutzung · pro Million Token2.500.000 Punkte
GLM-5-Turboglm-5-turboEigenständiges ModellZhipu · Produktiv2026-03-14Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated56.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 31.999 TokenEingabenutzung · pro Million Token1.369.863 PunkteCache-Treffernutzung · pro Million Token328.767 PunkteAusgabenutzung · pro Million Token6.027.397 Punkte
Input 32.000+ TokenEingabenutzung · pro Million Token1.917.808 PunkteCache-Treffernutzung · pro Million Token493.151 PunkteAusgabenutzung · pro Million Token7.123.288 Punkte
qwen-Tripo-P1.0qwen-tripo-tripo-p1.0Eigenständiges Modelltripo · Produktiv2026-03-11Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated43.2Preis-Leistung · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Tripo-H3.1qwen-tripo-tripo-h3.1Eigenständiges Modelltripo · Produktiv2026-03-06Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.9Preis-Leistung · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT-5.4gpt-5.4Eigenständiges ModellOpenAI · Produktiv2026-03-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated73.0Preis-Leistung · Estimated61.5
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token5.000.000 PunkteCache-Treffernutzung · pro Million Token500.000 PunkteAusgabenutzung · pro Million Token30.000.000 Punkte
GPT-5.4 Progpt-5.4-proEigenständiges ModellOpenAI · Produktiv2026-03-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated58.8Preis-Leistung · Estimated41.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token60.000.000 PunkteAusgabenutzung · pro Million Token360.000.000 Punkte
Qwen3.5-Omni-Flashqwen3.5-omni-flashEigenständiges ModellQwen · Produktiv2026-03 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated58.2Preis-Leistung · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3.5-Omni-Flash-Realtimeqwen3.5-omni-flash-realtimeEigenständiges ModellQwen · Produktiv2026-03 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3.5-Omni-Plusqwen3.5-omni-plusEigenständiges ModellQwen · Produktiv2026-03 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated54.5Preis-Leistung · Estimated53.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3.5-Omni-Plus-Realtimeqwen3.5-omni-plus-realtimeEigenständiges ModellQwen · Produktiv2026-03 (offiziell nur der Monat)Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-pixverse/pixverse-motioncontrolqwen-pixverse-pixverse-motioncontrolEigenständiges Modellpixverse · Produktiv2026-02-28Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT-5.3 Codexgpt-5.3-codexEigenständiges ModellOpenAI · Produktiv2026-02-24Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated58.5Preis-Leistung · Estimated52.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token3.500.000 PunkteCache-Treffernutzung · pro Million Token350.000 PunkteAusgabenutzung · pro Million Token28.000.000 Punkte
qwen-MiniMax-M2.5qwen-minimax-m2.5Eigenständiges ModellMiniMax · Produktiv2026-02-24Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated34.9Preis-Leistung · Estimated44.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token575.342 PunkteCache-Treffernutzung · pro Million Token115.068 PunkteAusgabenutzung · pro Million Token2.301.370 Punkte
GPT Audio 1.5gpt-audio-1.5Eigenständiges ModellOpenAI · Produktiv2026-02-23Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated52.6Preis-Leistung · Estimated41.6
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token5.000.000 PunkteAusgabenutzung · pro Million Token20.000.000 PunkteEingabenutzung · Audio · pro Million Token64.000.000 PunkteAusgabenutzung · Audio · pro Million Token128.000.000 Punkte
GPT Realtime 1.5gpt-realtime-1.5Eigenständiges ModellOpenAI · Produktiv2026-02-23Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated45.3Preis-Leistung · Estimated31.7
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token8.000.000 PunkteCache-Treffernutzung · pro Million Token800.000 PunkteAusgabenutzung · pro Million Token32.000.000 PunkteEingabenutzung · Bild · pro Million Token10.000.000 PunkteCache-Treffernutzung · Bild · pro Million Token1.000.000 PunkteEingabenutzung · Audio · pro Million Token64.000.000 PunkteCache-Treffernutzung · Audio · pro Million Token800.000 PunkteAusgabenutzung · Audio · pro Million Token128.000.000 Punkte
Qwen3.5-122B-A10Bqwen3.5-122b-a10bEigenständiges ModellQwen · Produktiv2026-02-23Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated46.4Preis-Leistung · Estimated55.2
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 128.000 TokenEingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token1.753.425 Punkte
Input 128.001+ TokenEingabenutzung · pro Million Token547.945 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token4.383.562 Punkte
Qwen3.5-27Bqwen3.5-27bEigenständiges ModellQwen · Produktiv2026-02-23Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated45.7Preis-Leistung · Estimated55.9
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 128.000 TokenEingabenutzung · pro Million Token164.384 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token1.315.068 Punkte
Input 128.001+ TokenEingabenutzung · pro Million Token493.151 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token3.945.205 Punkte
Qwen3.5-35B-A3Bqwen3.5-35b-a3bEigenständiges ModellQwen · Produktiv2026-02-23Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated42.9Preis-Leistung · Estimated55.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 128.000 TokenEingabenutzung · pro Million Token109.589 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token876.712 Punkte
Input 128.001+ TokenEingabenutzung · pro Million Token438.356 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token3.506.849 Punkte
Qwen3.5-Flashqwen3.5-flashEigenständiges ModellQwen · Produktiv2026-02-23Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated58.2Preis-Leistung · Estimated68.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 128.000 TokenEingabenutzung · pro Million Token54.795 PunkteCache-Treffernutzung · pro Million Token10.959 PunkteAusgabenutzung · pro Million Token547.945 Punkte
Input 128.001 – 256.000 TokenEingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token43.836 PunkteAusgabenutzung · pro Million Token2.191.781 Punkte
Input 256.001+ TokenEingabenutzung · pro Million Token328.767 PunkteCache-Treffernutzung · pro Million Token65.753 PunkteAusgabenutzung · pro Million Token3.287.671 Punkte
qwen-GLM-5qwen-glm-5Eigenständiges ModellZhipu · Produktiv2026-02-18Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated61.1Preis-Leistung · Estimated60.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 32.000 TokenEingabenutzung · pro Million Token1.095.890 PunkteCache-Treffernutzung · pro Million Token219.178 PunkteAusgabenutzung · pro Million Token4.931.507 Punkte
Input 32.001+ TokenEingabenutzung · pro Million Token1.643.836 PunkteCache-Treffernutzung · pro Million Token328.767 PunkteAusgabenutzung · pro Million Token6.027.397 Punkte
claude-sonnet-4-6claude-sonnet-4-6Eigenständiges ModellAnthropic · Produktiv2026-02-17Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated65.2Preis-Leistung · Estimated60.6
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

claude-sonnet-4-6-100claude-sonnet-4-6-100Eigenständiges ModellAnthropic · Produktiv2026-02-17Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated65.2Preis-Leistung · Estimated60.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3.5-397B-A17Bqwen3.5-397b-a17bEigenständiges ModellQwen · Produktiv2026-02-15Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated49.6Preis-Leistung · Estimated56.4
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 128.000 TokenEingabenutzung · pro Million Token328.767 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token1.972.603 Punkte
Input 128.001+ TokenEingabenutzung · pro Million Token821.918 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token4.931.507 Punkte
Qwen3.5-Plusqwen3.5-plusEigenständiges ModellQwen · Produktiv2026-02-15Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated54.5Preis-Leistung · Estimated61.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 128.000 TokenEingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token43.836 PunkteAusgabenutzung · pro Million Token1.315.068 Punkte
Input 128.001 – 256.000 TokenEingabenutzung · pro Million Token547.945 PunkteCache-Treffernutzung · pro Million Token109.589 PunkteAusgabenutzung · pro Million Token3.287.671 Punkte
Input 256.001+ TokenEingabenutzung · pro Million Token1.095.890 PunkteCache-Treffernutzung · pro Million Token219.178 PunkteAusgabenutzung · pro Million Token6.575.342 Punkte
qwen-MiniMax/MiniMax-M2.5qwen-minimax-minimax-m2.5Eigenständiges ModellMiniMax · Produktiv2026-02-12Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token575.342 PunkteCache-Treffernutzung · pro Million Token57.534 PunkteAusgabenutzung · pro Million Token2.301.370 Punkte
qwen-PixVerse-V5.6-r2vqwen-pixverse-pixverse-v5.6-r2vEigenständiges Modellpixverse · Produktiv2026-02-12Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ZHIPU/GLM-5qwen-zhipu-glm-5Eigenständiges ModellZhipu AI · Produktiv2026-02-12Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated31.2
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.643.836 PunkteCache-Treffernutzung · pro Million Token410.959 PunkteAusgabenutzung · pro Million Token6.027.397 Punkte
qwen-ViduQ3-Pro_start-end2videoqwen-vidu-viduq3-pro_start-end2videoEigenständiges Modellvidu · Produktiv2026-02-11Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-Turbo_img2videoqwen-vidu-viduq3-turbo_img2videoEigenständiges Modellvidu · Produktiv2026-02-11Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-Turbo_start-end2videoqwen-vidu-viduq3-turbo_start-end2videoEigenständiges Modellvidu · Produktiv2026-02-11Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-Turbo_text2videoqwen-vidu-viduq3-turbo_text2videoEigenständiges Modellvidu · Produktiv2026-02-11Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GLM-5glm-5Eigenständiges ModellZhipu · Produktiv2026-02-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.3Preis-Leistung · Estimated60.9
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 31.999 TokenEingabenutzung · pro Million Token1.095.890 PunkteCache-Treffernutzung · pro Million Token273.973 PunkteAusgabenutzung · pro Million Token4.931.507 Punkte
Input 32.000+ TokenEingabenutzung · pro Million Token1.643.836 PunkteCache-Treffernutzung · pro Million Token410.959 PunkteAusgabenutzung · pro Million Token6.027.397 Punkte
Qwen-Image-2.0qwen-image-2.0Eigenständiges ModellAlibaba Cloud · Produktiv2026-02-10Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated73.8Preis-Leistung · Estimated68.7
Estimate basis2026-10-08 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 · Independent
Ausgabenutzung · Bild · pro Bild54.795 Punkte
claude-opus-4-6claude-opus-4-6Eigenständiges ModellAnthropic · Produktiv2026-02-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated70.8Preis-Leistung · Estimated64.6
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

claude-opus-4-6-100claude-opus-4-6-100Eigenständiges ModellAnthropic · Produktiv2026-02-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated70.8Preis-Leistung · Estimated64.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Kling Image 3.0qwen-kling-kling-v3-image-generationEigenständiges Modellkling · Produktiv2026-02-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated73.8Preis-Leistung · Estimated66.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Kling Image 3.0 Omniqwen-kling-kling-v3-omni-image-generationEigenständiges Modellkling · Produktiv2026-02-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Kling Video 3.0 Omniqwen-kling-kling-v3-omni-video-generationEigenständiges Modellkling · Produktiv2026-02-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated41.7Preis-Leistung · Estimated44.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Kling Video 3.0qwen-kling-kling-v3-video-generationEigenständiges Modellkling · Produktiv2026-02-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Kimi-K2.5qwen-kimi-k2.5Eigenständiges ModellMoonshot · Produktiv2026-01-30Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated34.9Preis-Leistung · Estimated41.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.095.890 PunkteCache-Treffernutzung · pro Million Token219.178 PunkteAusgabenutzung · pro Million Token5.753.425 Punkte
Fun-ASR-Flash-8k实时语音识别fun-asr-flash-8k-realtimeEigenständiges ModellQwen · Produktiv2026-01-28Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ2-Pro_reference2videoqwen-vidu-viduq2-pro_reference2videoEigenständiges Modellvidu · Produktiv2026-01-27Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-Pro_img2videoqwen-vidu-viduq3-pro_img2videoEigenständiges Modellvidu · Produktiv2026-01-27Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-Pro_text2videoqwen-vidu-viduq3-pro_text2videoEigenständiges Modellvidu · Produktiv2026-01-27Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3-VL-Plusqwen3-vl-plusEigenständiges ModellQwen · Produktiv2026-01-26Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated42.7Preis-Leistung · Estimated51.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 32.000 TokenEingabenutzung · pro Million Token273.973 PunkteCache-Treffernutzung · pro Million Token54.795 PunkteAusgabenutzung · pro Million Token2.739.726 Punkte
Input 32.001 – 128.000 TokenEingabenutzung · pro Million Token410.959 PunkteCache-Treffernutzung · pro Million Token82.192 PunkteAusgabenutzung · pro Million Token4.109.589 Punkte
Input 128.001+ TokenEingabenutzung · pro Million Token821.918 PunkteCache-Treffernutzung · pro Million Token164.384 PunkteAusgabenutzung · pro Million Token8.219.178 Punkte
qwen-PixVerse-V5.6-it2vqwen-pixverse-pixverse-v5.6-it2vEigenständiges Modellpixverse · Produktiv2026-01-26Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-PixVerse-V5.6-kf2vqwen-pixverse-pixverse-v5.6-kf2vEigenständiges Modellpixverse · Produktiv2026-01-26Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-PixVerse-V5.6-t2vqwen-pixverse-pixverse-v5.6-t2vEigenständiges Modellpixverse · Produktiv2026-01-26Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Virtual Try On 001-100virtual-try-on-001Eigenständiges ModellGoogle · Produktiv2026-01-23Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.5Preis-Leistung · Estimated46.1
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT-5.2 Codexgpt-5.2-codexEigenständiges ModellOpenAI · Produktiv2026-01-14Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.0Preis-Leistung · Estimated54.5
Version comparison review8/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token3.500.000 PunkteCache-Treffernutzung · pro Million Token350.000 PunkteAusgabenutzung · pro Million Token28.000.000 Punkte
qwen-MiniMax/MiniMax-M2.1qwen-minimax-minimax-m2.1Eigenständiges ModellMiniMax · Produktiv2025-12-23Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token575.342 PunkteCache-Treffernutzung · pro Million Token57.534 PunkteAusgabenutzung · pro Million Token2.301.370 Punkte
GLM-4.7glm-4.7Eigenständiges ModellZhipu · Produktiv2025-12-22Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated60.2Preis-Leistung · Estimated60.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 31.999 Token · Output 0 – 199 TokenEingabenutzung · pro Million Token547.945 PunkteCache-Treffernutzung · pro Million Token109.589 PunkteAusgabenutzung · pro Million Token2.191.781 Punkte
Input 0 – 31.999 Token · Output 200+ TokenEingabenutzung · pro Million Token821.918 PunkteCache-Treffernutzung · pro Million Token164.384 PunkteAusgabenutzung · pro Million Token3.835.616 Punkte
Input 32.000+ TokenEingabenutzung · pro Million Token1.095.890 PunkteCache-Treffernutzung · pro Million Token219.178 PunkteAusgabenutzung · pro Million Token4.383.562 Punkte
GPT Image 1.5gpt-image-1.5Eigenständiges ModellOpenAI · Produktiv2025-12-16Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung76.0Preis-Leistung53.2
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Eingabenutzung · pro Million Token10.000.000 PunkteCache-Treffernutzung · pro Million Token2.500.000 PunkteEingabenutzung · Bild · pro Million Token16.000.000 PunkteCache-Treffernutzung · Bild · pro Million Token4.000.000 PunkteAusgabenutzung · pro Million Token20.000.000 PunkteAusgabenutzung · Bild · pro Million Token64.000.000 Punkte
Wan2.6-I2Vwan2.6-i2vEigenständiges ModellAlibaba Cloud · Produktiv2025-12-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung53.2Preis-Leistung45.3
Version comparison review
Vorläufig2026-10-08 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 · Independent
Videogenerierung 720P · pro Sekunde164.384 PunkteVideogenerierung 1080P · pro Sekunde273.973 Punkte
Wan2.6-Imagewan2.6-imageEigenständiges ModellAlibaba Cloud · Produktiv2025-12-16Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung31.6Preis-Leistung39.2
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Ausgabenutzung · Bild · pro Bild54.795 Punkte
qwen-Wan2.6-R2Vwan2.6-r2vEigenständiges ModellWan · Produktiv2025-12-16Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated55.3Preis-Leistung · Estimated53.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Wan2.6-T2Iwan2.6-t2iEigenständiges ModellAlibaba Cloud · Produktiv2025-12-16Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung50.0Preis-Leistung52.1
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Ausgabenutzung · Bild · pro Bild54.795 Punkte
Wan2.6-T2Vwan2.6-t2vEigenständiges ModellAlibaba Cloud · Produktiv2025-12-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung57.4Preis-Leistung48.3
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Videogenerierung 720P · pro Sekunde164.384 PunkteVideogenerierung 1080P · pro Sekunde273.973 Punkte
Cohere Rerank v4.0 Procohere-rerank-v4.0-proEigenständiges ModellCohere · Produktiv2025-12-11Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated65.8Preis-Leistung · Estimated61.1
Estimate basis2026-10-08 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 · Official
Neusortierung · pro 1.000 Sucheinheiten5.000.000 Punkte
GPT-5.2gpt-5.2Eigenständiges ModellOpenAI · Produktiv2025-12-11Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated61.7Preis-Leistung · Estimated54.3
Version comparison review12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token3.500.000 PunkteCache-Treffernutzung · pro Million Token350.000 PunkteAusgabenutzung · pro Million Token28.000.000 Punkte
GPT-5.1 Codex Maxgpt-5.1-codex-maxEigenständiges ModellOpenAI · Produktiv2025-12-04Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated72.5Preis-Leistung · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.500.000 PunkteCache-Treffernutzung · pro Million Token250.000 PunkteAusgabenutzung · pro Million Token20.000.000 Punkte
Mistral Large 3mistral-large-3Eigenständiges ModellMistral AI · Produktiv2025-12-02Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated60.6Preis-Leistung · Estimated60.8
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.000.000 PunkteAusgabenutzung · pro Million Token3.000.000 Punkte
qwen-ViduQ2-Pro-fast_img2videoqwen-vidu-viduq2-pro-fast_img2videoEigenständiges Modellvidu · Produktiv2025-12-02Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3-LiveTranslate-Flashqwen3-livetranslate-flashEigenständiges ModellQwen · Produktiv2025-12-01Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated58.2Preis-Leistung · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3-Omni-Flashqwen3-omni-flashEigenständiges ModellQwen · Produktiv2025-12-01Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated58.2Preis-Leistung · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-SiliconFlow DeepSeek-V3.2qwen-siliconflow-deepseek-v3.2Eigenständiges ModellDeepSeek · Produktiv2025-12-01Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated45.8Preis-Leistung · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Vanchin/DeepSeek-V3.2-thinkqwen-vanchin-deepseek-v3.2-thinkEigenständiges ModellDeepSeek · Produktiv2025-12-01Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated45.8Preis-Leistung · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3-TTS-Flash-Realtimeqwen3-tts-flash-realtimeEigenständiges ModellQwen · Produktiv2025-11-27Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Z-Image-Turboz-image-turboEigenständiges ModellAlibaba Cloud · Produktiv2025-11-26Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung28.8Preis-Leistung50.2
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Ausgabenutzung · Bild · pro Bild27.398 Punkte
FLUX.2 [flex]flux.2-flexEigenständiges ModellBlack Forest Labs · Produktiv2025-11-25Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung46.8Preis-Leistung32.8
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Eingabenutzung · Bild · pro Megapixel100.000 PunkteAusgabenutzung · Bild · pro Megapixel100.000 Punkte
FLUX.2 Proflux.2-proEigenständiges ModellBlack Forest Labs · Produktiv2025-11-25Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung49.9Preis-Leistung64.9
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Erstes Megapixel · pro Megapixel60.000 PunkteWeiteres Megapixel · pro Megapixel30.000 Punkte
claude-opus-4-5claude-opus-4-5Eigenständiges ModellAnthropic · Produktiv2025-11-24Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated67.9Preis-Leistung—
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 estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

claude-opus-4-5-100claude-opus-4-5-100Eigenständiges ModellAnthropic · Produktiv2025-11-24Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated67.9Preis-Leistung—
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 estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Grok 4.1 Fast Non-Reasoninggrok-4-1-fast-non-reasoningEigenständiges ModellxAI · Produktiv2025-11-19Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · 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 estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token400.000 PunkteCache-Treffernutzung · pro Million Token100.000 PunkteAusgabenutzung · pro Million Token1.000.000 Punkte
Grok 4.1 Fast Reasoninggrok-4-1-fast-reasoningEigenständiges ModellxAI · Produktiv2025-11-19Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated59.5Preis-Leistung · 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 estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token400.000 PunkteCache-Treffernutzung · pro Million Token100.000 PunkteAusgabenutzung · pro Million Token1.000.000 Punkte
Gemini 3 Pro Preview-100gemini-3-pro-previewEigenständiges ModellGoogle · Produktiv2025-11-18Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated69.4Preis-Leistung · Estimated63.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Veo 3.1 Fast Generate 001-100veo-3.1-fast-generate-001Eigenständiges ModellGoogle · Produktiv2025-11-17Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Veo 3.1 Generate 001-100veo-3.1-generate-001Eigenständiges ModellGoogle · Produktiv2025-11-17Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT-5.1gpt-5.1Eigenständiges ModellOpenAI · Produktiv2025-11-13Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated63.8Preis-Leistung · Estimated57.2
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.500.000 PunkteCache-Treffernutzung · pro Million Token250.000 PunkteAusgabenutzung · pro Million Token20.000.000 Punkte
GPT-5.1 Codexgpt-5.1-codexEigenständiges ModellOpenAI · Produktiv2025-11-13Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated63.6Preis-Leistung · Estimated57.1
1/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.500.000 PunkteCache-Treffernutzung · pro Million Token250.000 PunkteAusgabenutzung · pro Million Token20.000.000 Punkte
GPT-5.1 Codex Minigpt-5.1-codex-miniEigenständiges ModellOpenAI · Produktiv2025-11-13Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated43.1Preis-Leistung · Estimated49.4
1/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token500.000 PunkteCache-Treffernutzung · pro Million Token50.000 PunkteAusgabenutzung · pro Million Token4.000.000 Punkte
Lyria 002-100lyria-002Eigenständiges ModellGoogle · Produktiv2025-10-27Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ2_reference2videoqwen-vidu-viduq2_reference2videoEigenständiges Modellvidu · Produktiv2025-10-21Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ2_text2videoqwen-vidu-viduq2_text2videoEigenständiges Modellvidu · Produktiv2025-10-21Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Vanchin/DeepSeek-OCRqwen-vanchin-deepseek-ocrEigenständiges ModellDeepSeek · Produktiv2025-10-20Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated81.8Preis-Leistung · Estimated72.3
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

claude-haiku-4-5claude-haiku-4-5Eigenständiges ModellAnthropic · Produktiv2025-10-15Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated60.4Preis-Leistung · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

claude-haiku-4-5-100claude-haiku-4-5-100Eigenständiges ModellAnthropic · Produktiv2025-10-15Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated60.4Preis-Leistung · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT-5 Progpt-5-proEigenständiges ModellOpenAI · Produktiv2025-10-06Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.5Preis-Leistung · Estimated41.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token20.000.000 PunkteAusgabenutzung · pro Million Token240.000.000 Punkte
GPT Audio Minigpt-audio-miniEigenständiges ModellOpenAI · Produktiv2025-10-06Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated52.6Preis-Leistung · Estimated66.8
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token1.200.000 PunkteAusgabenutzung · pro Million Token4.800.000 PunkteEingabenutzung · Audio · pro Million Token20.000.000 PunkteAusgabenutzung · Audio · pro Million Token40.000.000 Punkte
GPT Image 1 Minigpt-image-1-miniEigenständiges ModellOpenAI · Produktiv2025-10-06Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung20.1Preis-Leistung44.1
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Eingabenutzung · pro Million Token4.000.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteEingabenutzung · Bild · pro Million Token5.000.000 PunkteCache-Treffernutzung · Bild · pro Million Token500.000 PunkteAusgabenutzung · Bild · pro Million Token16.000.000 Punkte
GPT Realtime Minigpt-realtime-miniEigenständiges ModellOpenAI · Produktiv2025-10-06Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated54.0Preis-Leistung · Estimated67.8
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token1.200.000 PunkteCache-Treffernutzung · pro Million Token120.000 PunkteAusgabenutzung · pro Million Token4.800.000 PunkteEingabenutzung · Bild · pro Million Token1.600.000 PunkteCache-Treffernutzung · Bild · pro Million Token160.000 PunkteEingabenutzung · Audio · pro Million Token20.000.000 PunkteCache-Treffernutzung · Audio · pro Million Token600.000 PunkteAusgabenutzung · Audio · pro Million Token40.000.000 Punkte
Gemini 2.5 Flash TTS-100gemini-2.5-flash-ttsEigenständiges ModellGoogle · Produktiv2025-09-30Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated87.1Preis-Leistung · Estimated76.0
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Gemini 2.5 Pro TTS-100gemini-2.5-pro-ttsEigenständiges ModellGoogle · Produktiv2025-09-30Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated82.6Preis-Leistung · Estimated72.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sora 2sora-2Eigenständiges ModellOpenAI · Vorschau2025-09-30Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung66.0Preis-Leistung50.4
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Videogenerierung · pro Sekunde200.000 Punkte
claude-sonnet-4-5claude-sonnet-4-5Eigenständiges ModellAnthropic · Produktiv2025-09-29Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated61.6Preis-Leistung · Estimated58.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ2-Pro_img2videoqwen-vidu-viduq2-pro_img2videoEigenständiges Modellvidu · Produktiv2025-09-24Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ2-Pro_start-end2videoqwen-vidu-viduq2-pro_start-end2videoEigenständiges Modellvidu · Produktiv2025-09-24Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ2-Turbo_img2videoqwen-vidu-viduq2-turbo_img2videoEigenständiges Modellvidu · Produktiv2025-09-24Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ2-Turbo_start-end2videoqwen-vidu-viduq2-turbo_start-end2videoEigenständiges Modellvidu · Produktiv2025-09-24Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT-5 Codexgpt-5-codexEigenständiges ModellOpenAI · Produktiv2025-09-23Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated59.1Preis-Leistung · Estimated53.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.500.000 PunkteCache-Treffernutzung · pro Million Token250.000 PunkteAusgabenutzung · pro Million Token20.000.000 Punkte
qwen-SiliconFlow DeepSeek-V3.1-Terminusqwen-siliconflow-deepseek-v3.1-terminusEigenständiges ModellDeepSeek · Produktiv2025-09-22Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.9Preis-Leistung · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Vanchin/DeepSeek-V3.1-Terminusqwen-vanchin-deepseek-v3.1-terminusEigenständiges ModellDeepSeek · Produktiv2025-09-22Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.9Preis-Leistung · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3-TTS-Flashqwen3-tts-flashEigenständiges ModellAlibaba Cloud · Produktiv2025-09 (offiziell nur der Monat)Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated74.4Preis-Leistung · Estimated82.1
Estimate basis2026-10-08 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 · Official
Audio · pro 10.000 Zeichen219.179 Punkte
Chirp 3-100chirp-3Eigenständiges ModellGoogle · Produktiv2025-08-29Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT Realtimegpt-realtimeEigenständiges ModellOpenAI · Produktiv2025-08-28Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated59.9Preis-Leistung · Estimated41.9
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token8.000.000 PunkteCache-Treffernutzung · pro Million Token800.000 PunkteAusgabenutzung · pro Million Token32.000.000 PunkteEingabenutzung · Bild · pro Million Token10.000.000 PunkteCache-Treffernutzung · Bild · pro Million Token1.000.000 PunkteEingabenutzung · Audio · pro Million Token64.000.000 PunkteCache-Treffernutzung · Audio · pro Million Token800.000 PunkteAusgabenutzung · Audio · pro Million Token128.000.000 Punkte
GPT-5gpt-5Eigenständiges ModellOpenAI · Produktiv2025-08-07Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated58.7Preis-Leistung · Estimated53.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.500.000 PunkteCache-Treffernutzung · pro Million Token250.000 PunkteAusgabenutzung · pro Million Token20.000.000 Punkte
GPT-5 Minigpt-5-miniEigenständiges ModellOpenAI · Produktiv2025-08-07Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated43.1Preis-Leistung · Estimated49.4
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token500.000 PunkteCache-Treffernutzung · pro Million Token50.000 PunkteAusgabenutzung · pro Million Token4.000.000 Punkte
GPT-5 Nanogpt-5-nanoEigenständiges ModellOpenAI · Produktiv2025-08-07Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated44.4Preis-Leistung · Estimated57.0
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token100.000 PunkteCache-Treffernutzung · pro Million Token10.000 PunkteAusgabenutzung · pro Million Token800.000 Punkte
GPT-OSS 120B-100openai-gpt-oss-120b-maas-001Eigenständiges ModellOpenAI · Produktiv2025-08-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated57.3Preis-Leistung · Estimated55.1
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3-Coder-Flashqwen3-coder-flashEigenständiges ModellQwen · Produktiv2025-08-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated58.2Preis-Leistung · Estimated64.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 32.000 TokenEingabenutzung · pro Million Token273.973 PunkteCache-Treffernutzung · pro Million Token54.795 PunkteAusgabenutzung · pro Million Token1.095.890 Punkte
Input 32.001 – 128.000 TokenEingabenutzung · pro Million Token410.959 PunkteCache-Treffernutzung · pro Million Token82.192 PunkteAusgabenutzung · pro Million Token1.643.836 Punkte
Input 128.001 – 256.000 TokenEingabenutzung · pro Million Token684.932 PunkteCache-Treffernutzung · pro Million Token136.986 PunkteAusgabenutzung · pro Million Token2.739.726 Punkte
Input 256.001+ TokenEingabenutzung · pro Million Token1.369.863 PunkteCache-Treffernutzung · pro Million Token273.973 PunkteAusgabenutzung · pro Million Token6.849.315 Punkte
Qwen-Flashqwen-flashEigenständiges ModellQwen · Produktiv2025-08-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated59.4Preis-Leistung · Estimated70.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 128.000 TokenEingabenutzung · pro Million Token41.096 PunkteCache-Treffernutzung · pro Million Token8.219 PunkteAusgabenutzung · pro Million Token410.959 Punkte
Input 128.001 – 256.000 TokenEingabenutzung · pro Million Token164.384 PunkteCache-Treffernutzung · pro Million Token32.877 PunkteAusgabenutzung · pro Million Token1.643.836 Punkte
Input 256.001+ TokenEingabenutzung · pro Million Token328.767 PunkteCache-Treffernutzung · pro Million Token65.753 PunkteAusgabenutzung · pro Million Token3.287.671 Punkte
doubao-glm-4-5-airdoubao-glm-4-5-air-20250728Fester Snapshot / Version · Einziger ZugangZhipu AI · Produktiv2025-07-28Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GLM-4.5-Airglm-4.5-airEigenständiges ModellZhipu · Produktiv2025-07-27Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated59.3Preis-Leistung · Estimated64.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 31.999 Token · Output 0 – 199 TokenEingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token43.836 PunkteAusgabenutzung · pro Million Token547.945 Punkte
Input 0 – 31.999 Token · Output 200+ TokenEingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token43.836 PunkteAusgabenutzung · pro Million Token1.643.836 Punkte
Input 32.000+ TokenEingabenutzung · pro Million Token328.767 PunkteCache-Treffernutzung · pro Million Token65.753 PunkteAusgabenutzung · pro Million Token2.191.781 Punkte
qwen-pixverse/pixverse-lipsyncqwen-pixverse-pixverse-lipsyncEigenständiges Modellpixverse · Produktiv2025-07-14Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Plusqwen-plusEigenständiges ModellQwen · Produktiv2025-06-24Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated44.2Preis-Leistung · Estimated55.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Input 0 – 128.000 TokenEingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token43.836 PunkteAusgabenutzung · pro Million Token547.945 Punkte
Input 128.001 – 256.000 TokenEingabenutzung · pro Million Token657.534 PunkteCache-Treffernutzung · pro Million Token131.507 PunkteAusgabenutzung · pro Million Token5.479.452 Punkte
Input 256.001+ TokenEingabenutzung · pro Million Token1.315.068 PunkteCache-Treffernutzung · pro Million Token263.014 PunkteAusgabenutzung · pro Million Token13.150.685 Punkte
qwen-SiliconFlow DeepSeek-R1-0528qwen-siliconflow-deepseek-r1-0528Eigenständiges ModellDeepSeek · Produktiv2025-05-28Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated43.2Preis-Leistung · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Mistral OCR 2505-100mistralai-mistral-ocr-2505-001Eigenständiges ModellMistral AI · Produktiv2025-05-22Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated81.8Preis-Leistung · Estimated72.3
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

mistral-medium-2505mistral-medium-2505Eigenständiges ModellMistral AI · Produktiv2025-05-07Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated54.1Preis-Leistung · Estimated52.9
Version comparison review4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Phi-4 Reasoningphi-4-reasoningEigenständiges ModellMicrosoft · Produktiv2025-04-30Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token250.000 PunkteAusgabenutzung · pro Million Token1.000.000 Punkte
o3o3Eigenständiges ModellOpenAI · Produktiv2025-04-16Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.8Preis-Leistung · Estimated56.1
7/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token4.000.000 PunkteCache-Treffernutzung · pro Million Token1.000.000 PunkteAusgabenutzung · pro Million Token16.000.000 Punkte
Veo 2.0 Generate 001-100veo-2.0-generate-001Eigenständiges ModellGoogle · Produktiv2025-04-09Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Llama 4 Maverick 17B 128Ellama-4-maverick-17b-128e-instruct-fp8Eigenständiges ModellMeta · Produktiv2025-04-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated60.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token500.000 PunkteAusgabenutzung · pro Million Token2.000.000 Punkte
Llama 4 Maverick 17B 128E-100llama-4-maverick-17b-128e-instruct-maas-100Eigenständiges ModellMeta · Produktiv2025-04-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Llama 4 Scout 17B 16E Instruct-100meta-llama-4-scout-17b-16e-instruct-maas-001Eigenständiges ModellMeta · Produktiv2025-04-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated53.1Preis-Leistung · Estimated52.2
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-SiliconFlow DeepSeek-V3-0324qwen-siliconflow-deepseek-v3-0324Eigenständiges ModellDeepSeek · Produktiv2025-03-24Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated39.9Preis-Leistung · Estimated42.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

GPT-4o Mini Transcribegpt-4o-mini-transcribeEigenständiges ModellOpenAI · Produktiv2025-03-20Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.4Preis-Leistung · Estimated94.0
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · Audio · pro Million Token6.000.000 PunkteEingabenutzung · pro Million Token2.500.000 PunkteAusgabenutzung · pro Million Token10.000.000 Punkte
GPT-4o Mini TTSgpt-4o-mini-ttsEigenständiges ModellOpenAI · Produktiv2025-03-20Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated59.8Preis-Leistung · Estimated56.9
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token1.200.000 PunkteAusgabenutzung · Audio · pro Million Token24.000.000 Punkte
GPT-4o Transcribegpt-4o-transcribeEigenständiges ModellOpenAI · Produktiv2025-03-20Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung91.4Preis-Leistung64.0
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 18%qwen-asr-report · Independent
Eingabenutzung · Audio · pro Million Token12.000.000 PunkteEingabenutzung · pro Million Token5.000.000 PunkteAusgabenutzung · pro Million Token20.000.000 Punkte
mistral-small-2503mistral-small-2503Eigenständiges ModellMistral AI · Produktiv2025-03-17Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.0Preis-Leistung—
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 estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Mistral Small 3.1-100mistral-small-2503-100Eigenständiges ModellGoogle · Vorschau2025-03-17Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.0Preis-Leistung · 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 estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token200.000 PunkteAusgabenutzung · pro Million Token600.000 Punkte
Text Embedding Large Exp 03 07-100text-embedding-large-exp-03-07Eigenständiges ModellGoogle · Produktiv2025-03-07Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-DeepSeek-R1-Distill-Qwen-1.5Bqwen-deepseek-r1-distill-qwen-1.5bEigenständiges ModellDeepSeek · Produktiv2025-01-20Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated43.2Preis-Leistung · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Codestral 2501codestral-2501Eigenständiges ModellMistral AI · Produktiv2025-01-13Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated60.1
9/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token600.000 PunkteAusgabenutzung · pro Million Token1.800.000 Punkte
Ministral-3Bministral-3bEigenständiges ModellMistral AI · Produktiv2024-10-16Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated49.2Preis-Leistung · Estimated49.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Longqwen-longEigenständiges ModellQwen · Produktiv2024-05-20Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated52.5Preis-Leistung · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token136.986 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token547.945 Punkte
Text Embedding 3 Largetext-embedding-3-largeEigenständiges ModellOpenAI · Produktiv2024-01-25Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung64.6Preis-Leistung45.2
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · Official
Embedding-Eingabe · pro Million Token260.000 Punkte
Text Embedding 3 Smalltext-embedding-3-smallEigenständiges ModellOpenAI · Produktiv2024-01-25Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung62.3Preis-Leistung71.3
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · Official
Embedding-Eingabe · pro Million Token40.000 Punkte
Cohere-embed-v3-englishcohere-embed-v3-englishEigenständiges ModellCohere · Produktiv2023-11-02Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Cohere-embed-v3-multilingualcohere-embed-v3-multilingualEigenständiges ModellCohere · Produktiv2023-11-02Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Text Embedding Ada 002text-embedding-ada-002Eigenständiges ModellOpenAI · Produktiv2022-12-15Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung61.0Preis-Leistung46.6
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · Official
Embedding-Eingabe · pro Million Token200.000 Punkte
Qwen-Image-2.1-Turboqwen-image-2.1-turboEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-14Kein Festpreis; Abrechnung nach Dienst
Leistung—Preis-Leistung—
Nicht bewertet

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Chirp 2-100chirp-2-001Eigenständiges ModellGoogle · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

语音生成CosyVoice-v3.5-flash大模型cosyvoice-v3.5-flashEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated75.4Preis-Leistung · Estimated67.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

语音生成CosyVoice-v3.5-plus大模型cosyvoice-v3.5-plusEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated75.4Preis-Leistung · Estimated67.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

doubao-GLM-5.3-Flashdoubao-glm-5-3-flash-260828Fester Snapshot / Version · Einziger ZugangZhipu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token63.014 PunkteAusgabenutzung · pro Million Token767.123 Punkte
qwen2-5-72bdoubao-qwen2-5-72b-20240919Fester Snapshot / Version · Einziger ZugangQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen3-0-6bdoubao-qwen3-0-6b-20250429Fester Snapshot / Version · Einziger ZugangQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen3-14bdoubao-qwen3-14b-20250429Fester Snapshot / Version · Einziger ZugangQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen3-32bdoubao-qwen3-32b-20250429Fester Snapshot / Version · Einziger ZugangQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen3-8bdoubao-qwen3-8b-20250429Fester Snapshot / Version · Einziger ZugangQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

doubao-seed-translationdoubao-seed-translation-250915Fester Snapshot / Version · Einziger ZugangDoubao · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

doubao-smart-routerdoubao-smart-router-250928Fester Snapshot / Version · Einziger ZugangDoubao · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated50.0Preis-Leistung · Estimated50.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

FaceChain人物图像检测facechain-facedetectEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.5Preis-Leistung · Estimated46.1
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Fun-ASR语音识别fun-asrEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Fun-ASR实时语音识别fun-asr-realtimeEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

音乐生成 Previewfun-music-previewEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

音乐生成fun-music-v1Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Grok 4.20 Non-Reasoning-100grok-4-20-non-reasoning-100Eigenständiges ModellxAI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung—
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 estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token2.500.000 PunkteCache-Treffernutzung · pro Million Token400.000 PunkteAusgabenutzung · pro Million Token5.000.000 Punkte
Grok 4.20 Reasoning-100grok-4-20-reasoning-100Eigenständiges ModellxAI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung—
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 estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Grok 4.3-100grok-4.3-100Eigenständiges ModellxAI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.8Preis-Leistung—
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 estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-HappyHorse-1.0-Video-Edithappyhorse-1.0-video-editEigenständiges ModellHappyHorse · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated80.9Preis-Leistung · Estimated71.6
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

图像擦除补全image-erase-completionEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.5Preis-Leistung · Estimated46.1
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

人物实例分割image-instance-segmentationEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.5Preis-Leistung · Estimated46.1
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Codestral 2-100mistralai-codestral-2-001Eigenständiges ModellMistral AI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Mistral Medium 3-100mistralai-mistral-medium-3-001Eigenständiges ModellMistral AI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Paraformer语音识别-8k-v2paraformer-8k-v2Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Paraformer实时语音识别-8k-v2paraformer-realtime-8k-v2Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Paraformer实时语音识别-v2paraformer-realtime-v2Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Paraformer语音识别-v2paraformer-v2Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3-ASR-Flash-Filetransqwen3-asr-flash-filetransEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen3-ASR-Flash-Realtimeqwen3-asr-flash-realtimeEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.6Preis-Leistung · Estimated51.8
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Audio-3.1-ASR-Flashqwen-audio-3.1-asr-flashEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Audio-3.1-ASR-Flash-Filetransqwen-audio-3.1-asr-flash-filetransEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Audio-3.1-ASR-Flash-Messageqwen-audio-3.1-asr-flash-messageEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Audio-3.1-ASR-Flash-Streamingqwen-audio-3.1-asr-flash-streamingEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated91.4Preis-Leistung · Estimated79.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Audio-3.1-TTS-Flashqwen-audio-3.1-tts-flashEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated74.4Preis-Leistung · Estimated67.1
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Audio-3.1-TTS-Nextqwen-audio-3.1-tts-nextEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated74.4Preis-Leistung · Estimated67.1
Estimate basis2026-10-08 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 · Official

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Doc-Turboqwen-doc-turboEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated48.7Preis-Leistung · Estimated49.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token164.384 PunkteCache-Treffernutzung · pro Million Token32.877 PunkteAusgabenutzung · pro Million Token273.973 Punkte
Qwen-Flash-Characterqwen-flash-characterEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated59.9Preis-Leistung · Estimated70.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token68.493 PunkteCache-Treffernutzung · pro Million Token13.699 PunkteAusgabenutzung · pro Million Token410.959 Punkte
qwen-Kling Video 3.0 Turboqwen-kling-kling-v3-turbo-video-generationEigenständiges Modellkling · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-speech-02-hdqwen-minimax-speech-02-hdEigenständiges Modellmini-max · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated32.9Preis-Leistung · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-speech-02-turboqwen-minimax-speech-02-turboEigenständiges Modellmini-max · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated34.1Preis-Leistung · Estimated38.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-speech-2.8-hdqwen-minimax-speech-2.8-hdEigenständiges Modellmini-max · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.1Preis-Leistung · Estimated45.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-speech-2.8-turboqwen-minimax-speech-2.8-turboEigenständiges Modellmini-max · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated46.9Preis-Leistung · Estimated47.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-MT-Flashqwen-mt-flashEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated59.4Preis-Leistung · Estimated56.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-MT-Imageqwen-mt-imageEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated34.1Preis-Leistung · Estimated38.9
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-MT-Liteqwen-mt-liteEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.3Preis-Leistung · Estimated54.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-MT-Plusqwen-mt-plusEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated46.7Preis-Leistung · Estimated47.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-PixVerse-V6-r2vqwen-pixverse-pixverse-v6-r2vEigenständiges Modellpixverse · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Plus-Characterqwen-plus-characterEigenständiges Modellqwen-domain-model · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated46.9Preis-Leistung · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token219.178 PunkteCache-Treffernutzung · pro Million Token43.836 PunkteAusgabenutzung · pro Million Token547.945 Punkte
qwen-stepfun/step-5-previewqwen-stepfun-step-5-previewEigenständiges ModellStepFun · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated30.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token1.917.808 PunkteCache-Treffernutzung · pro Million Token95.890 PunkteAusgabenutzung · pro Million Token5.479.452 Punkte
qwen-unisound/unisound-u2qwen-unisound-unisound-u2Eigenständiges Modellunisound · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated32.9Preis-Leistung · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Vanchin/DeepSeek-R1qwen-vanchin-deepseek-r1Eigenständiges ModellDeepSeek · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated43.2Preis-Leistung · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Vanchin/DeepSeek-V3qwen-vanchin-deepseek-v3Eigenständiges ModellDeepSeek · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated42.6Preis-Leistung · Estimated44.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-vanchin/deepseek-v4-proqwen-vanchin-deepseek-v4-proEigenständiges ModellDeepSeek · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated71.1Preis-Leistung · Estimated64.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Vidu-image-lite_reference2imageqwen-vidu-vidu-image-lite_reference2imageEigenständiges Modellvidu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated66.4Preis-Leistung · Estimated61.5
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Vidu-image-pro_reference2imageqwen-vidu-vidu-image-pro_reference2imageEigenständiges Modellvidu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated66.4Preis-Leistung · Estimated61.5
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Vidu-image_reference2imageqwen-vidu-vidu-image_reference2imageEigenständiges Modellvidu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated73.8Preis-Leistung · Estimated66.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ2-fast_reference2imageqwen-vidu-viduq2-fast_reference2imageEigenständiges Modellvidu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated66.4Preis-Leistung · Estimated61.5
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ2-Pro_reference2imageqwen-vidu-viduq2-pro_reference2imageEigenständiges Modellvidu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated66.4Preis-Leistung · Estimated61.5
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-Ad_reference2videoqwen-vidu-viduq3-ad_reference2videoEigenständiges Modellvidu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-Drama_reference2videoqwen-vidu-viduq3-drama_reference2videoEigenständiges Modellvidu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-fast_reference2imageqwen-vidu-viduq3-fast_reference2imageEigenständiges Modellvidu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated85.0Preis-Leistung · Estimated74.5
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ViduQ3-Pro-fast_img2videoqwen-vidu-viduq3-pro-fast_img2videoEigenständiges Modellvidu · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Qwen-Voice-Enrollmentqwen-voice-enrollmentEigenständiger DiensteintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-ZHIPU/GLM-5.3-FlashXqwen-zhipu-glm-5.3-flashxEigenständiges ModellZhipu AI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated41.0Preis-Leistung · Estimated37.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token547.945 PunkteCache-Treffernutzung · pro Million Token156.164 PunkteAusgabenutzung · pro Million Token1.917.808 Punkte
Sambert语音合成-Bethsambert-beth-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Bettysambert-betty-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Briansambert-brian-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Callysambert-cally-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Camilasambert-camila-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Cindysambert-cindy-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Clarasambert-clara-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Donnasambert-donna-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Evasambert-eva-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Hannasambert-hanna-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Indahsambert-indah-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Perlasambert-perla-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-Waansambert-waan-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知厨sambert-zhichu-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知达sambert-zhida-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知德sambert-zhide-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知飞sambert-zhifei-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知柜sambert-zhigui-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.5Preis-Leistung · Estimated46.1
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知浩sambert-zhihao-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知佳sambert-zhijia-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知婧sambert-zhijing-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知伦sambert-zhilun-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知猫sambert-zhimao-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知妙(多情感)sambert-zhimiao-emo-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知茗sambert-zhiming-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知墨sambert-zhimo-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知楠sambert-zhinan-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知娜sambert-zhina-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知倩sambert-zhiqian-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知琪sambert-zhiqi-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知茹sambert-zhiru-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知硕sambert-zhishuo-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知树sambert-zhishu-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知莎sambert-zhistella-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知婷sambert-zhiting-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知薇sambert-zhiwei-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知祥sambert-zhixiang-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知笑sambert-zhixiao-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知雅sambert-zhiya-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知晔sambert-zhiye-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知颖sambert-zhiying-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知媛sambert-zhiyuan-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Sambert语音合成-知悦sambert-zhiyue-v1Eigenständiger StimmeintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

鞋靴模特shoemodel-v1Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.5Preis-Leistung · Estimated46.1
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

语音识别热词speech-biasingEigenständiger DiensteintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

通用文本向量-async-v1text-embedding-async-v1Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

通用文本向量-async-v2text-embedding-async-v2Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

意图分类模型tongyi-intent-detect-v3Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

伶鹊-对话分析-flashtongyi-xiaomi-analysis-flashEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token54.795 PunkteCache-Treffernutzung · pro Million Token10.959 PunkteAusgabenutzung · pro Million Token109.589 Punkte
伶鹊-对话分析-protongyi-xiaomi-analysis-proEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token273.973 PunkteCache-Treffernutzung · pro Million Token54.795 PunkteAusgabenutzung · pro Million Token739.726 Punkte
Translate LLM-100translate-llmEigenständiges ModellGoogle · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

声动人像VideoRetalkvideoretalkEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

视频风格重绘video-style-transformEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.0Preis-Leistung · Estimated50.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

虚拟模特V2virtualmodel-v2Eigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated44.5Preis-Leistung · Estimated46.1
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

大模型声音复刻及声音设计voice-enrollmentEigenständiger DiensteintragQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated56.6Preis-Leistung · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.2-Animate-Mixwan2.2-animate-mixEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.2-Animate-Movewan2.2-animate-moveEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.2-KF2V-Flashwan2.2-kf2v-flashEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-通义万相2.2-数字人-S2Vwan2.2-s2vEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.2-S2V-Detectwan2.2-s2v-detectEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.2-T2I-Flashwan2.2-t2i-flashEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.2-T2I-Pluswan2.2-t2i-plusEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.5-I2I-Previewwan2.5-i2i-previewEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated52.7Preis-Leistung · Estimated51.9
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.5-T2I-Previewwan2.5-t2i-previewEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated51.5Preis-Leistung · Estimated51.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.6-R2V-Flashwan2.6-r2v-flashEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated55.3Preis-Leistung · Estimated53.7
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.0-T2I-Turbowanx2.0-t2i-turboEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.1-ImageEditwanx2.1-imageeditEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.1-KF2V-Pluswanx2.1-kf2v-plusEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.1-T2I-Pluswanx2.1-t2i-plusEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.1-T2I-Turbowanx2.1-t2i-turboEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-Wan2.1-VACE-Pluswanx2.1-vace-plusEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-创意海报生成wanx-poster-generation-v1Eigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-万相-涂鸦作画wanx-sketch-to-image-liteEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated34.8Preis-Leistung · Estimated39.4
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-人像风格重绘wanx-style-repaint-v1Eigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-wanx-t2iwanx-v1Eigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-虚拟模特wanx-virtualmodelEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated36.9Preis-Leistung · Estimated40.8
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

qwen-万相-图像局部重绘wanx-x-paintingEigenständiges ModellWan · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-10-05Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated37.0Preis-Leistung · Estimated40.9
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

语音生成cosyvoice-v2大模型cosyvoice-v2Eigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated75.4Preis-Leistung · Estimated52.8
Estimate basis2026-10-08 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 · Official
Audio · pro 10.000 Zeichen547.946 Punkte
语音生成CosyVoice-v3-flash大模型cosyvoice-v3-flashEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated75.4Preis-Leistung · Estimated75.5
Estimate basis2026-10-08 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 · Official
Audio · pro 10.000 Zeichen273.973 Punkte
语音生成CosyVoice-v3-plus大模型cosyvoice-v3-plusEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated75.4Preis-Leistung · Estimated52.8
Estimate basis2026-10-08 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 · Official
Audio · pro 10.000 Zeichen547.946 Punkte
GUI-Plusgui-plusEigenständiges ModellQwen · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated56.6Preis-Leistung · Estimated61.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · pro Million Token410.959 PunkteCache-Treffernutzung · pro Million Token0 PunkteAusgabenutzung · pro Million Token1.232.877 Punkte
通用多模态向量multimodal-embedding-v1Eigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.3Preis-Leistung · Estimated48.1
Estimate basis2026-10-08 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 · Official
Embedding-Eingabe · pro Million Token191.781 PunkteEingabenutzung · Bild · pro Million Token246.576 PunkteVideoeingabe · pro Million Token246.576 Punkte
Qwen2.5-VL-Embeddingqwen2.5-vl-embeddingEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.3Preis-Leistung · Estimated48.1
Estimate basis2026-10-08 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 · Official
Embedding-Eingabe · pro Million Token191.781 PunkteEingabenutzung · Bild · pro Million Token493.151 Punkte
Qwen3-ASR-Flashqwen3-asr-flashEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.4Preis-Leistung · Estimated94.0
Estimate basis2026-10-08 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 · Independent
Transkription · pro Sekunde61 Punkte
千问3-Rerankqwen3-rerankEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated72.5Preis-Leistung · Estimated80.8
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token136.987 Punkte
Qwen3-VL-Embeddingqwen3-vl-embeddingEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.3Preis-Leistung · Estimated48.1
Estimate basis2026-10-08 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 · Official
Embedding-Eingabe · pro Million Token191.781 PunkteEingabenutzung · Bild · pro Million Token493.151 Punkte
Qwen3-VL-Rerankqwen3-vl-rerankEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated72.5Preis-Leistung · Estimated80.8
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token136.987 PunkteVideoeingabe · pro Million Token493.154 Punkte

Vom Kunden bestätigter vorläufiger Haftungspreis für Videoeingaben. Der Anbieter hat weder einen offiziellen Videopreis noch eine Umrechnung von Frames in Token veröffentlicht. Er dient nur der Kataloganzeige und Testreservierung, wird nicht als Anbieterkosten verbucht und ändert keine früheren Abrechnungen.

Qwen-Image-2.0-Proqwen-image-2.0-proEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated66.4Preis-Leistung · Estimated46.5
Estimate basis2026-10-08 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 · Independent
Ausgabenutzung · Bild · pro Bild136.987 Punkte
Qwen-Image-3.0-Proqwen-image-3.0-proEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung85.0Preis-Leistung59.5
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Bild Eingabenutzung 1K · pro Bild5.480 PunkteBild Eingabenutzung 2K · pro Bild5.480 PunkteBild Ausgabenutzung 1K · pro Bild68.494 PunkteBild Ausgabenutzung 2K · pro Bild136.987 Punkte
QwenVL-OCRqwen-vl-ocrEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated81.8Preis-Leistung · Estimated72.3
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token82.192 PunkteAusgabenutzung · pro Million Token136.987 Punkte
通用文本向量-v1text-embedding-v1Eigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung58.3Preis-Leistung45.3
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official
Embedding-Eingabe · pro Million Token191.781 Punkte
通用文本向量-v2text-embedding-v2Eigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung60.1Preis-Leistung46.6
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official
Embedding-Eingabe · pro Million Token191.781 Punkte
通用文本向量-v3text-embedding-v3Eigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung63.4Preis-Leistung53.9
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official
Embedding-Eingabe · pro Million Token136.987 Punkte
通用文本向量-v4text-embedding-v4Eigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung71.6Preis-Leistung59.6
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official
Embedding-Eingabe · pro Million Token136.987 Punkte
视觉向量-flashtongyi-embedding-vision-flashEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.3Preis-Leistung · Estimated70.9
Estimate basis2026-10-08 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 · Official
Embedding-Eingabe · pro Million Token41.096 Punkte
视觉向量-plustongyi-embedding-vision-plusEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated62.3Preis-Leistung · Estimated53.1
Estimate basis2026-10-08 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 · Official
Embedding-Eingabe · pro Million Token136.987 Punkte
Wan2.2-I2V-Flashwan2.2-i2v-flashEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated11.7Preis-Leistung · Estimated38.2
Estimate basis2026-10-08 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 · Independent
Videogenerierung 480P · pro Sekunde27.398 PunkteVideogenerierung 720P · pro Sekunde54.795 PunkteVideogenerierung 1080P · pro Sekunde131.507 Punkte
Wan2.2-I2V-Pluswan2.2-i2v-plusEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent
Videogenerierung 480P · pro Sekunde38.357 PunkteVideogenerierung 1080P · pro Sekunde191.781 Punkte
Wan2.2-T2V-Pluswan2.2-t2v-plusEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated11.7Preis-Leistung · Estimated23.2
Estimate basis2026-10-08 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 · Independent
Videogenerierung 480P · pro Sekunde38.357 PunkteVideogenerierung 1080P · pro Sekunde191.781 Punkte
Wan2.5-I2V-Previewwan2.5-i2v-previewEigenständiges ModellAlibaba Cloud · VorschauKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung55.3Preis-Leistung46.8
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Videogenerierung 480P · pro Sekunde82.192 PunkteVideogenerierung 720P · pro Sekunde164.384 PunkteVideogenerierung 1080P · pro Sekunde273.973 Punkte
Wan2.5-T2V-Previewwan2.5-t2v-previewEigenständiges ModellAlibaba Cloud · VorschauKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung48.9Preis-Leistung42.3
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Videogenerierung 480P · pro Sekunde82.192 PunkteVideogenerierung 720P · pro Sekunde164.384 PunkteVideogenerierung 1080P · pro Sekunde273.973 Punkte
wan2.6-I2V-flashwan2.6-i2v-flashEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated54.9Preis-Leistung · Estimated60.3
Estimate basis2026-10-08 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 · Independent
Videogenerierung 720P · pro Sekunde82.192 PunkteVideogenerierung 1080P · pro Sekunde136.987 Punkte
Wan2.1-I2V-Pluswanx2.1-i2v-plusEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated11.7Preis-Leistung · Estimated13.2
Estimate basis2026-10-08 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 · Independent
Videogenerierung 720P · pro Sekunde191.781 Punkte
Wan2.1-I2V-Turbowanx2.1-i2v-turboEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated11.7Preis-Leistung · Estimated34.6
Estimate basis2026-10-08 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 · Independent
Videogenerierung 480P · pro Sekunde65.754 PunkteVideogenerierung 720P · pro Sekunde65.754 Punkte
Wan2.1-T2V-Pluswanx2.1-t2v-plusEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated11.7Preis-Leistung · Estimated13.2
Estimate basis2026-10-08 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 · Independent
Videogenerierung 720P · pro Sekunde191.781 Punkte
Wan2.1-T2V-Turbowanx2.1-t2v-turboEigenständiges ModellAlibaba Cloud · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-10Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated11.7Preis-Leistung · Estimated34.6
Estimate basis2026-10-08 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 · Independent
Videogenerierung 480P · pro Sekunde65.754 PunkteVideogenerierung 720P · pro Sekunde65.754 Punkte
doubao-hitem3d-2-0-251223doubao-hitem3d-2-0-251223Fester Snapshot / Version · Einziger ZugangHitem3D · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-09Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated82.2Preis-Leistung · Estimated57.5
Estimate basis2026-10-08 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 · Official
Ausgabenutzung · 3D · pro Million Token21.917.809 Punkte
doubao-hyper3d-gen2-260112doubao-hyper3d-gen2-260112Fester Snapshot / Version · Einziger ZugangHyper3D · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-09Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated82.2Preis-Leistung · Estimated87.5
Estimate basis2026-10-08 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 · Official
Ausgabenutzung · 3D · pro Million Token16.438.357 Punkte
doubao-seedance-2-0-260128doubao-seedance-2-0-260128Fester Snapshot / Version · Einziger ZugangByteDance · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-09Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.5Preis-Leistung · Estimated68.5
Estimate basis2026-10-08 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 · Independent
Ausgabenutzung · Videogenerierung · pro Million Token12.602.740 Punkte
doubao-seedance-2-0-fast-260128doubao-seedance-2-0-fast-260128Fester Snapshot / Version · Einziger ZugangByteDance · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-09Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.5Preis-Leistung · Estimated70.8
Estimate basis2026-10-08 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 · Independent
Ausgabenutzung · Videogenerierung · pro Million Token7.602.740 Punkte
doubao-seedance-2-0-mini-260615doubao-seedance-2-0-mini-260615Fester Snapshot / Version · Einziger ZugangByteDance · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-09Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.5Preis-Leistung · Estimated75.9
Estimate basis2026-10-08 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 · Independent
Ausgabenutzung · Videogenerierung · pro Million Token2.520.548 Punkte
doubao-seedream-5-0-260128doubao-seedream-5-0-260128Fester Snapshot / Version · Einziger ZugangByteDance · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-09-09Verfügbar · Erzeugung und BearbeitungLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated54.4Preis-Leistung · Estimated53.4
Estimate basis2026-10-08 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 · Independent
Ausgabenutzung · Bild · pro Bild60.274 Punkte
GPT-4o Transcribe Diarizegpt-4o-transcribe-diarizeEigenständiges ModellOpenAI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-08-28Verfügbar · AudiowerkzeugeLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated91.4Preis-Leistung · Estimated64.0
Estimate basis2026-10-08 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 · Independent
Eingabenutzung · Audio · pro Million Token12.000.000 PunkteEingabenutzung · pro Million Token5.000.000 PunkteAusgabenutzung · pro Million Token20.000.000 Punkte
GPT Audiogpt-audioEigenständiges ModellOpenAI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-08-28Voller FunktionsumfangLetzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung · Estimated52.6Preis-Leistung · Estimated36.8
Estimate basis2026-10-08 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 · Official
Eingabenutzung · pro Million Token5.000.000 PunkteAusgabenutzung · pro Million Token20.000.000 PunkteEingabenutzung · Audio · pro Million Token80.000.000 PunkteAusgabenutzung · Audio · pro Million Token160.000.000 Punkte
Mistral Document AI 2512mistral-document-ai-2512Eigenständiges ModellMistral AI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-08-28Letzte Preisprüfung
Prüfung ausstehend (UTC+8)
Leistung96.1Preis-Leistung76.1
Vorläufig2026-10-08 16:22 (UTC+8) · Confidence 18%mistral-ocr · Official
Dokumentverarbeitung · pro 1.000 Seiten6.000.000 Punkte
Model Routermodel-routerEigenständiger RoutingdienstOpenAI · ProduktivKatalogaufnahme (Veröffentlichung offen): 2026-08-28Kein Festpreis; Abrechnung nach Dienst
Leistung · Estimated50.0Preis-Leistung · Estimated50.0
Estimate basis2026-10-08 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 · Independent

Dynamischer Preis: Router-Eingabeaufschlag plus Punkte des tatsächlich gewählten Modells.

Beschreibungen geprüfter Fähigkeiten · 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.

AKTUELLE GRENZE

Aktuelle Grenze

32 Modelle ohne Google hinzugefügt: 27 Textmodelle, Mistral Document AI, drei Embedding-Modelle und Sora 2. Connector 1.0.86.0 installieren und die Plugins sowie API-Key-Berechtigungen aktivieren. Text-API: 34 Modelle; Codex-Menü: 32 mit Werkzeugen. Phi und Llama dienen nur API-Fragen. Dokumente: 30 MB und 30 Seiten. Wissenssuche in ausgewählten lokalen Texten mit Quellen und wiederverwendbaren Indizes. Video: 4/8/12 Sekunden, 720p, Referenzbilder und Remix fertiger Videos. Videos zeitnah herunterladen. Abrechnung abgeschlossener Nutzung; lokale Cache-Lesezugriffe kostenlos. Google und model-router bleiben ausgeschlossen. Anlagenidentitäten, Protokolle, Betriebsdaten, Agenten und Steuerung bleiben in der vom Kunden autorisierten lokalen, Edge- oder privaten Umgebung. Die öffentliche Website informiert nur und ist keine Cloud-Steuerungsplattform.

ProjektanfrageAnmelden