HENGCDHENGCD INDUSTRIAL AIMODEL PRICING
Clear model prices and points
View model pricing, connector integration and availability in one place. Actual access depends on the current API key and server route.
01
What this page covers
View model pricing, connector integration and availability in one place. Actual access depends on the current API key and server route.
This overview is translated for international visitors. Detailed technical and contractual wording follows the Chinese version.
Counts follow each entry’s released model list, with each model counted once per studio. A model may appear in multiple studios. Actual access and capabilities depend on API key permissions, server routes and the model’s details.
Completed capability declarations: 44. Each covers its stated deployment scope; model notes retain limits and pending items.
Token rates are shown per million Tokens. Other capabilities use their stated units. Context and processing tiers follow each model’s published tariff. Account points use actual consumption; the API Key coefficient applies only to Key points. Enabled services deduct points according to actual usage. Online top-ups and invoicing remain unavailable.
ModelPoint consumption
Independent models are shown first. A snapshot or alias is included only when it is the sole available entry for the same platform, generation and capability family. All identities keeps other versions and unverified entries searchable, with their own codes, prices and availability. Pending evidence or an unresolved identity relation does not mean the model is unavailable. Voice and service entries are not new foundation models. Classification does not change existing API routes or certification.
Shown / total: 482 / 613Claude Haiku 5.5
Awaiting verification (UTC+8)
claude-haiku-5-5Independent modelAnthropic · GA2026-10-07Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance—Value—
Not ratedInput usage · per million Tokens200,000 pointsCache-hit usage · per million Tokens20,000 pointsCache-write usage · 5m · per million Tokens250,000 pointsCache-write usage · 1h · per million Tokens400,000 pointsOutput usage · per million Tokens1,000,000 pointsWeb search · per 1,000 search units20,000,000 points
Claude Haiku 5.5-100
claude-haiku-5-5-100Independent modelAnthropic · GA2026-10-07No fixed price; billed by the underlying servicePerformance · Estimated74.7Value · Estimated82.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
Not rated · 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.Dynamic: router input markup plus the points for the model selected for each request.
Gemini Nano Banana 2.1-100
Awaiting verification (UTC+8)
gemini-nano-banana-2.1Independent modelGoogle · GA2026-10-06Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance92.5Value · Estimated66.5
Provisional
Not rated · Confidence 0%Input usage · per million Tokens3,000,000 pointsInput usage · Image · per million Tokens3,000,000 pointsCache-hit usage · per million Tokens300,000 pointsOutput usage · per million Tokens15,000,000 pointsCache-hit usage · Image · per million Tokens300,000 pointsOutput usage · Image · per million Tokens60,000,000 points
Qwen-Image-2.1-Pro
Awaiting verification (UTC+8)
qwen-image-2.1-proIndependent modelQwen · GA2026-10-02Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated66.4Value · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentOutput usage · Image · per image68,494 points
Grok 4.7-100
Awaiting verification (UTC+8)
grok-4.7-100Independent modelxAI · Preview2026-09-30Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance—Value—
Not ratedInput usage · per million Tokens4,000,000 pointsCache-hit usage · per million Tokens1,000,000 pointsOutput usage · per million Tokens12,000,000 points
GPT-6.1 Sol
Awaiting verification (UTC+8)
gpt-6.1-solIndependent modelOpenAI · GA2026-09-29Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated82.2Value · Estimated69.2
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.4 (estimated) · 5/19 observed / reasoning 85.3 (estimated) · 3/13 observed / writing 84.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-6-astra · 1 benchmarksReference: gpt-6-luna · 1 benchmarksReference: gpt-6-sol · 1 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens4,000,000 pointsCache-hit usage · per million Tokens200,000 pointsCache-write usage · per million Tokens5,000,000 pointsOutput usage · per million Tokens20,000,000 points
Claude Sonnet 5.5
Awaiting verification (UTC+8)
claude-sonnet-5-5Independent modelAnthropic · GA2026-09-28Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated74.4Value · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 84.5 (estimated) · 5/19 observed / reasoning 78.8 (estimated) · 3/13 observed / writing 59.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens4,000,000 pointsCache-hit usage · per million Tokens400,000 pointsCache-write usage · 5m · per million Tokens5,000,000 pointsCache-write usage · 1h · per million Tokens8,000,000 pointsOutput usage · per million Tokens20,000,000 pointsWeb search · per 1,000 search units20,000,000 points
Claude Sonnet 5.5-100
claude-sonnet-5-5-100Independent modelAnthropic · GA2026-09-28No fixed price; billed by the underlying servicePerformance · Estimated74.4Value · Estimated67.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 84.5 (estimated) · 0/19 observed / reasoning 78.8 (estimated) · 0/13 observed / writing 59.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-5-5 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
决策模型（预览版）
Awaiting verification (UTC+8)
decision-model-previewIndependent modelQwen · GA2026-09-24Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens0 points
Gemini 3.8 Live-100
Awaiting verification (UTC+8)
gemini-3.8-liveIndependent modelGoogle · GA2026-09-24Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated76.9Value · Estimated68.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.9 (estimated) · 0/19 observed / reasoning 76.8 (estimated) · 0/13 observed / writing 87.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.8-flash-high · 7 benchmarksReference: gemini-4-argon-high · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,500,000 pointsVideo input · per million Tokens2,000,000 pointsInput usage · Audio · per million Tokens6,000,000 pointsOutput usage · per million Tokens9,000,000 pointsOutput usage · Audio · per million Tokens24,000,000 pointsOutput usage · Video generation · per million Tokens2,000,000 points
Claude Opus 5.5
Awaiting verification (UTC+8)
claude-opus-5-5Independent modelAnthropic · GA2026-09-22Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated86.9Value · Estimated69.6
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 91.4 (estimated) · 5/19 observed / reasoning 94.0 (estimated) · 4/13 observed / writing 75.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens8,000,000 pointsCache-hit usage · per million Tokens400,000 pointsCache-write usage · 5m · per million Tokens10,000,000 pointsCache-write usage · 1h · per million Tokens16,000,000 pointsOutput usage · per million Tokens40,000,000 pointsWeb search · per 1,000 search units20,000,000 points
Claude Opus 5.5-100
claude-opus-5-5-100Independent modelAnthropic · GA2026-09-22No fixed price; billed by the underlying servicePerformance · Estimated86.9Value · Estimated75.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 91.4 (estimated) · 0/19 observed / reasoning 94.0 (estimated) · 0/13 observed / writing 75.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-5-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT-6 Luna
Awaiting verification (UTC+8)
gpt-6-lunaIndependent modelOpenAI · GA2026-09-22Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated59.4Value · Estimated65.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.8 (estimated) · 5/19 observed / reasoning 64.0 (estimated) · 4/13 observed / writing 50.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.6-luna by 4.3 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens200,000 pointsCache-hit usage · per million Tokens20,000 pointsCache-write usage · per million Tokens250,000 pointsOutput usage · per million Tokens1,000,000 points
GPT-6 Sol
Awaiting verification (UTC+8)
gpt-6-solIndependent modelOpenAI · GA2026-09-22Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated74.3Value · Estimated63.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 74.6 (estimated) · 5/19 observed / reasoning 78.4 (estimated) · 4/13 observed / writing 69.9 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.6-sol by 8.8 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens4,000,000 pointsCache-hit usage · per million Tokens400,000 pointsCache-write usage · per million Tokens5,000,000 pointsOutput usage · per million Tokens20,000,000 points
Grok 4.7
Awaiting verification (UTC+8)
grok-4.7Independent modelxAI · GA2026-09-21Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance—Value—
Not ratedInput usage · per million Tokens4,000,000 pointsCache-hit usage · per million Tokens1,000,000 pointsOutput usage · per million Tokens12,000,000 points
Qwen-Audio-3.1-Realtime-Plus
qwen-audio-3.1-realtime-plusIndependent modelQwen · GA2026-09-20No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Qwen3.8-Livetranslate-Flash-Realtime
qwen3.8-livetranslate-flash-realtimeIndependent modelQwen · GA2026-09-18No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Qwen-MT-Uni
qwen-mt-uniIndependent modelQwen · GA2026-09-16No fixed price; billed by the underlying servicePerformance · Estimated49.4Value · Estimated49.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.5 (estimated) · 0/19 observed / reasoning 54.8 (estimated) · 0/13 observed / writing 47.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: qwen-14b-chat · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-kimi/kimi-k2.8-preview
Awaiting verification (UTC+8)
qwen-kimi-kimi-k2.8-previewIndependent modelMoonshot AI · GA2026-09-11Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,780,822 pointsCache-hit usage · per million Tokens465,753 pointsOutput usage · per million Tokens7,397,260 points
DeepSeek V4.1 Flash
Awaiting verification (UTC+8)
deepseek-flashIndependent modelDeepSeek · GA2026-09-10Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated78.1Value · Estimated77.6
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 81.2 (estimated) · 4/19 observed / reasoning 82.4 (estimated) · 4/13 observed / writing 70.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksEstimated value uses this exact model's reviewed off-peak public point rates and the shared text workload. Weekday peak rates double; public holidays use off-peak rates. It is not a measured charge.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput usage · per million Tokens300,000 pointsCache-hit usage · per million Tokens6,000 pointsOutput usage · per million Tokens1,200,000 points
doubao-deepseek-v4-1-flash
Awaiting verification (UTC+8)
doubao-deepseek-v4-1-flash-260910Fixed snapshot / version · Sole entryDeepSeek · GA2026-09-10Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens273,973 pointsCache-hit usage · per million Tokens5,479 pointsOutput usage · per million Tokens1,095,890 points
qwen-DeepSeek V4.1 Flash
Awaiting verification (UTC+8)
qwen-deepseek-v4.1-flashIndependent modelDeepSeek · GA2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated61.4Value · Estimated66.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens273,973 pointsCache-hit usage · per million Tokens27,397 pointsOutput usage · per million Tokens1,095,890 points
qwen-vanchin/deepseek-v4.1-flash
qwen-vanchin-deepseek-v4.1-flashIndependent modelDeepSeek · GA2026-09-10No fixed price; billed by the underlying servicePerformance · Estimated61.4Value · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT Image 2.5 Flare
Awaiting verification (UTC+8)
gpt-image-2.5-flareIndependent modelOpenAI · GA2026-09-08Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance98.5Value70.3
Input usage · per million Tokens10,000,000 pointsCache-hit usage · per million Tokens2,500,000 pointsInput usage · Image · per million Tokens16,000,000 pointsCache-hit usage · Image · per million Tokens4,000,000 pointsOutput usage · Image · per million Tokens60,000,000 points
GPT Image 2.5 Sunburst
Awaiting verification (UTC+8)
gpt-image-2.5-sunburstIndependent modelOpenAI · GA2026-09-08Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance100.0Value71.4
Input usage · per million Tokens10,000,000 pointsCache-hit usage · per million Tokens2,500,000 pointsInput usage · Image · per million Tokens16,000,000 pointsCache-hit usage · Image · per million Tokens4,000,000 pointsOutput usage · Image · per million Tokens60,000,000 points
GPT-6 Astra
Awaiting verification (UTC+8)
gpt-6-astraIndependent modelOpenAI · GA2026-09-03Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated85.4Value · Estimated64.8
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 79.9 (estimated) · 5/19 observed / reasoning 92.0 (estimated) · 4/13 observed / writing 84.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens20,000,000 pointsCache-hit usage · per million Tokens2,000,000 pointsCache-write usage · per million Tokens25,000,000 pointsOutput usage · per million Tokens100,000,000 points
Gemini 3.8 Flash-100
Awaiting verification (UTC+8)
gemini-3.8-flash-100Independent modelGoogle · GA2026-09-02Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance—Value—
Not ratedInput usage · per million Tokens3,000,000 pointsInput usage · Image · per million Tokens3,000,000 pointsInput usage · Audio · per million Tokens3,000,000 pointsVideo input · per million Tokens3,000,000 pointsCache-hit usage · per million Tokens300,000 pointsOutput usage · per million Tokens15,000,000 pointsCache-write usage · per million Tokens3,000,000 pointsExplicit cache storage · per million token-hours2,000,000 points
Claude Fable 5.1
Awaiting verification (UTC+8)
claude-fable-5-1Independent modelAnthropic · GA2026-09-01Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated89.2Value · Estimated67.4
Shared exact-model performance from claude-fable-5-1; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 90.5 (estimated) · 5/19 observed / reasoning 93.8 (estimated) · 4/13 observed / writing 83.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens20,000,000 pointsCache-hit usage · per million Tokens500,000 pointsCache-write usage · 5m · per million Tokens25,000,000 pointsCache-write usage · 1h · per million Tokens40,000,000 pointsOutput usage · per million Tokens100,000,000 pointsWeb search · per 1,000 search units20,000,000 points
Claude Fable 5.1-100
claude-fable-5-1-100Independent modelAnthropic · GA2026-09-01No fixed price; billed by the underlying servicePerformance · Estimated89.2Value—
Shared exact-model performance from claude-fable-5-1; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 90.5 (estimated) · 5/19 observed / reasoning 93.8 (estimated) · 4/13 observed / writing 83.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialDynamic: router input markup plus the points for the model selected for each request.
Doubao-Seed-2.1-Lite
Awaiting verification (UTC+8)
doubao-seed-2-1-lite-260915Fixed snapshot / version · Sole entryDoubao · GA2026-09 (official month only)Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated63.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 56.6microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens43,836 pointsOutput usage · per million Tokens739,726 points
doubao-seedream-5-0-flash
doubao-seedream-5-0-flash-260915Fixed snapshot / version · Sole entryDoubao · GA2026-09 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated65.8Value · Estimated61.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-5.0-lite · 50.2Reference: seedream-5.0-pro · 85.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
千问3.7-通用文本向量-flash
Awaiting verification (UTC+8)
qwen3.7-text-embedding-flashIndependent modelAlibaba Cloud · GA2026-09-01Last price verificationAwaiting verification (UTC+8)
Performance · Estimated62.3Value · Estimated73.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEmbedding input · per million Tokens34,247 points
千问3.7-通用文本重排序
Awaiting verification (UTC+8)
qwen3.7-text-rerankIndependent modelAlibaba Cloud · GA2026-09-01Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated72.5Value · Estimated80.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · OfficialInput usage · per million Tokens136,987 points
Qwen3.8-Omni-Flash
qwen3.8-omni-flashIndependent modelQwen · GA2026-09 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated61.4Value · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3.8-Omni-Flash-Realtime
qwen3.8-omni-flash-realtimeIndependent modelQwen · GA2026-09 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Qwen-MT-Image-2.0
qwen-mt-image-2.0Independent modelQwen · GA2026-08-28No fixed price; billed by the underlying servicePerformance · Estimated73.8Value · Estimated66.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Cohere Parse v5
Awaiting verification (UTC+8)
cohere-parse-v5Independent modelCohere · Preview2026-08-27Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance79.2Value85.4
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 18%cohere-parsebench · OfficialDocument processing · per 1,000 pages3,000,000 points
Gemini Omni 1.1 Flash Preview-100
gemini-omni-1.1-flash-previewIndependent modelGoogle · GA2026-08-27No fixed price; billed by the underlying servicePerformance · Estimated49.9Value · Estimated49.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.2 (estimated) · 0/19 observed / reasoning 44.4 (estimated) · 0/13 observed / writing 59.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.5-flash-high · 7 benchmarksReference: gemini-1.5-flash-001 · 4 benchmarksReference: gemini-1.5-flash-002 · 4 benchmarksReference: gemini-1.5-flash-8b-001 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ZHIPU/GLM-5.3-Flash
Awaiting verification (UTC+8)
qwen-zhipu-glm-5.3-flashIndependent modelZhipu AI · GA2026-08-26Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated48.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens63,014 pointsOutput usage · per million Tokens767,123 points
Qwen3.8-Flash
Awaiting verification (UTC+8)
qwen3.8-flashIndependent modelQwen · GA2026-08-25Last price verificationAwaiting verification (UTC+8)
Performance · Estimated61.4Value · Estimated67.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens27,397 pointsOutput usage · per million Tokens739,726 points
qwen-Kimi-K3
Awaiting verification (UTC+8)
qwen-kimi-k3Independent modelMoonshot · GA2026-08-19Last price verificationAwaiting verification (UTC+8)
Performance · Estimated39.7Value · Estimated38.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 35.6 (estimated) · 0/19 observed / reasoning 49.2 (estimated) · 0/13 observed / writing 34.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens5,479,452 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens27,397,260 points
Qwen3.8-27B
Awaiting verification (UTC+8)
qwen3.8-27bIndependent modelQwen · GA2026-08-17Last price verificationAwaiting verification (UTC+8)
Performance · Estimated65.0Value · Estimated64.2
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 5/19 observed / reasoning 68.3 (estimated) · 4/13 observed / writing 62.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens821,918 pointsCache-hit usage · per million Tokens164,384 pointsOutput usage · per million Tokens3,287,671 points
qwen-GLM-5.3
Awaiting verification (UTC+8)
qwen-glm-5.3Independent modelZhipu AI · GA2026-08-14Last price verificationAwaiting verification (UTC+8)
Performance · Estimated61.1Value · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens7,671,233 points
qwen-ZHIPU/GLM-5.3
Awaiting verification (UTC+8)
qwen-zhipu-glm-5.3Independent modelZhipu AI · GA2026-08-14Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens7,671,233 points
DeepSeek V4 Pro
Awaiting verification (UTC+8)
deepseek-v4-proIndependent modelDeepSeek · GA2026-08-13Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated64.4Value · Estimated62.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.8 (estimated) · 0/19 observed / reasoning 74.3 (estimated) · 0/13 observed / writing 65.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: deepseek-v4-pro · 7 benchmarksReference: deepseek-v4-pro-0813 · 7 benchmarksReference: deepseek-v4-pro · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,320,000 pointsCache-hit usage · per million Tokens44,000 pointsOutput usage · per million Tokens3,960,000 points
GLM-5.3
Awaiting verification (UTC+8)
glm-5.3Independent modelZhipu · GA2026-08-13Last price verificationAwaiting verification (UTC+8)
Performance · Estimated71.7Value · Estimated65.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.9 (estimated) · 0/19 observed / reasoning 71.1 (estimated) · 0/13 observed / writing 70.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.3 · 7 benchmarksReference: glm-5.2 · 6 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens7,671,233 points
GLM-5.3-Flash
Awaiting verification (UTC+8)
glm-5.3-flashIndependent modelZhipu · GA2026-08-13Last price verificationAwaiting verification (UTC+8)
Performance · Estimated65.1Value · Estimated70.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 69.5 (estimated) · 0/19 observed / reasoning 68.7 (estimated) · 0/13 observed / writing 57.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: glm-5.3-flash · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens63,014 pointsOutput usage · per million Tokens767,123 points
Grok 4.6
Awaiting verification (UTC+8)
grok-4.6Independent modelxAI · Preview2026-08-12Last price verificationAwaiting verification (UTC+8)
Performance · Estimated70.4Value · Estimated61.9
Shared exact-model performance from grok-4.6; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.3 (estimated) · 5/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 73.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens8,000,000 pointsCache-hit usage · per million Tokens2,000,000 pointsOutput usage · per million Tokens24,000,000 points
Grok 4.6-100
grok-4.6-100Independent modelxAI · GA2026-08-12No fixed price; billed by the underlying servicePerformance · Estimated70.4Value—
Shared exact-model performance from grok-4.6; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.3 (estimated) · 5/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 73.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialDynamic: router input markup plus the points for the model selected for each request.
MAI Thinking 1
Awaiting verification (UTC+8)
mai-thinking-1Independent modelMicrosoft AI · Preview2026-08-12Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated51.7
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 18%coding 56.8 (estimated) · 4/19 observed / reasoning 60.2 (estimated) · 5/13 observed / writing 52.8 (estimated) · 3/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens4,000,000 pointsCache-hit usage · per million Tokens400,000 pointsOutput usage · per million Tokens16,000,000 points
Qwen3.8-2.4T-A95B
Awaiting verification (UTC+8)
qwen3.8-2.4t-a95bIndependent modelQwen · GA2026-08-12Last price verificationAwaiting verification (UTC+8)
Performance · Estimated65.0Value · Estimated58.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 0/19 observed / reasoning 68.3 (estimated) · 0/13 observed / writing 62.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-27b · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens3,287,671 pointsCache-hit usage · per million Tokens410,959 pointsOutput usage · per million Tokens9,863,014 points
万相3.0-视频生成
Awaiting verification (UTC+8)
wan3.0-videoIndependent modelAlibaba Cloud · GA2026-08-06Last price verificationAwaiting verification (UTC+8)
Performance · Estimated92.6Value · Estimated72.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan3.0 · 92.6arena · Independentarena · IndependentVideo generation 480P · per second57,535 pointsVideo generation 720P · per second115,069 pointsVideo generation 1080P · per second230,137 points
Qwen3.8-Max
Awaiting verification (UTC+8)
qwen3.8-maxIndependent modelQwen · GA2026-08-02Last price verificationAwaiting verification (UTC+8)
Performance · Estimated76.0Value · Estimated66.6
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 70.3 (estimated) · 5/19 observed / reasoning 82.3 (estimated) · 4/13 observed / writing 75.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens3,287,671 pointsCache-hit usage · per million Tokens410,959 pointsOutput usage · per million Tokens9,863,014 points
Gemini 3.5 Transcribe Live Preview-100
gemini-3.5-transcribe-live-previewIndependent modelGoogle · GA2026-08 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
Gemini 3.5 Transcribe Preview-100
gemini-3.5-transcribe-previewIndependent modelGoogle · GA2026-08 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
doubao-DeepSeek V4 Flash GA (2026-07-31)
Awaiting verification (UTC+8)
doubao-deepseek-v4-flash-ga-260731Fixed snapshot / version · Sole entryDeepSeek · GA2026-07-31Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated58.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens821,918 pointsCache-hit usage · per million Tokens27,397 pointsOutput usage · per million Tokens2,465,753 points
qwen-MiniMax/MiniMax-H3
qwen-minimax-minimax-h3Independent modelmini-max · GA2026-07-31No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Audio-3.0-ASR-Flash
Awaiting verification (UTC+8)
qwen-audio-3.0-asr-flashIndependent modelAlibaba Cloud · GA2026-07-30Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated91.4Value · Estimated94.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · per second61 points
qwen-audio-3.0-asr-flash-filetrans
qwen-audio-3.0-asr-flash-filetransIndependent modelQwen · GA2026-07-30No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Audio-3.0-ASR-Flash-Streaming
qwen-audio-3.0-asr-flash-streamingIndependent modelQwen · GA2026-07-30No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT Live Transcribe
Awaiting verification (UTC+8)
gpt-live-transcribeIndependent modelOpenAI · GA2026-07-28Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated91.4Value · Estimated64.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · per hour2,040,000 points
GPT Transcribe
Awaiting verification (UTC+8)
gpt-transcribeIndependent modelOpenAI · GA2026-07-28Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated91.4Value · Estimated81.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · per hour540,000 points
qwen-PixVerse-V6-r2v-omni
qwen-pixverse-pixverse-v6-r2v-omniIndependent modelpixverse · GA2026-07-26No fixed price; billed by the underlying servicePerformance · Estimated61.1Value · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Claude Opus 5
Awaiting verification (UTC+8)
claude-opus-5Independent modelAnthropic · GA2026-07-24Last price verificationAwaiting verification (UTC+8)
Performance · Estimated81.9Value · Estimated65.2
Shared exact-model performance from claude-opus-5; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.2 (estimated) · 5/19 observed / reasoning 86.3 (estimated) · 4/13 observed / writing 74.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens10,000,000 pointsCache-hit usage · per million Tokens1,000,000 pointsCache-write usage · 5m · per million Tokens12,500,000 pointsCache-write usage · 1h · per million Tokens20,000,000 pointsOutput usage · per million Tokens50,000,000 points
Claude Opus 5-100
claude-opus-5-100Independent modelAnthropic · GA2026-07-24No fixed price; billed by the underlying servicePerformance · Estimated81.9Value—
Shared exact-model performance from claude-opus-5; coverage refers to public model benchmarks, not tests of every platform deployment.Version comparison review13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.2 (estimated) · 5/19 observed / reasoning 86.3 (estimated) · 4/13 observed / writing 74.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-opus-5-5-100 by 5.0 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialDynamic: router input markup plus the points for the model selected for each request.
Gemini 3.5 Flash-Lite-100
Awaiting verification (UTC+8)
gemini-3.5-flash-lite-100Independent modelGoogle · GA2026-07-21Last price verificationAwaiting verification (UTC+8)
Performance · Estimated52.3Value · Estimated55.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.1 (estimated) · 0/19 observed / reasoning 52.8 (estimated) · 0/13 observed / writing 56.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.5-flash-lite-high · 7 benchmarksReference: gemini-3.5-flash-lite · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens600,000 pointsCache-hit usage · per million Tokens60,000 pointsOutput usage · per million Tokens5,000,000 points
Qwen3.7-Flash
Awaiting verification (UTC+8)
qwen3.7-flashIndependent modelQwen · GA2026-07-21Last price verificationAwaiting verification (UTC+8)
Performance · Estimated61.4Value · Estimated73.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32,000 TokenInput usage · per million Tokens54,795 pointsCache-hit usage · per million Tokens10,959 pointsOutput usage · per million Tokens219,178 points
Input 32,001 – 256,000 TokenInput usage · per million Tokens164,384 pointsCache-hit usage · per million Tokens32,877 pointsOutput usage · per million Tokens657,534 points
Input 256,001+ TokenInput usage · per million Tokens328,767 pointsCache-hit usage · per million Tokens65,753 pointsOutput usage · per million Tokens1,315,068 points
Qwen-Image-3.0
Awaiting verification (UTC+8)
qwen-image-3.0Independent modelAlibaba Cloud · GA2026-07-21Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance · Estimated73.8Value · Estimated81.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8arena · Independentarena · IndependentImage Input usage 1K · per image5,480 pointsImage Input usage 2K · per image5,480 pointsImage Output usage 1K · per image49,316 pointsImage Output usage 2K · per image49,316 points
Kimi K3
Awaiting verification (UTC+8)
kimi-k3Independent modelMoonshot · GA2026-07-16Last price verificationAwaiting verification (UTC+8)
Performance · Estimated80.1Value · Estimated66.4
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 81.7 (estimated) · 5/19 observed / reasoning 80.2 (estimated) · 4/13 observed / writing 78.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens5,479,452 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens27,397,260 points
qwen-kimi/kimi-k3
Awaiting verification (UTC+8)
qwen-kimi-kimi-k3Independent modelMoonshot AI · GA2026-07-16Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens5,479,452 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens27,397,260 points
Qwen3.7-通用文本向量
Awaiting verification (UTC+8)
qwen3.7-text-embeddingIndependent modelAlibaba Cloud · GA2026-07-15Last price verificationAwaiting verification (UTC+8)
Performance · Estimated62.3Value · Estimated53.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEmbedding input · per million Tokens136,987 points
Qwen-Audio-3.0-Realtime-Flash
qwen-audio-3.0-realtime-flashIndependent modelQwen · GA2026-07-14No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Qwen-Audio-3.0-Realtime-Plus
qwen-audio-3.0-realtime-plusIndependent modelQwen · GA2026-07-14No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
GPT-5.6 Luna
Awaiting verification (UTC+8)
gpt-5.6-lunaIndependent modelOpenAI · GA2026-07-09Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated63.7Value · Estimated65.5
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 4/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 54.0 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput usage · per million Tokens400,000 pointsCache-hit usage · per million Tokens40,000 pointsCache-write usage · per million Tokens500,000 pointsOutput usage · per million Tokens2,400,000 points
GPT-5.6 Sol
Awaiting verification (UTC+8)
gpt-5.6-solIndependent modelOpenAI · GA2026-07-09Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated83.1Value · Estimated67.0
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 77.4 (estimated) · 4/19 observed / reasoning 89.4 (estimated) · 4/13 observed / writing 82.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput usage · per million Tokens8,000,000 pointsCache-hit usage · per million Tokens800,000 pointsCache-write usage · per million Tokens10,000,000 pointsOutput usage · per million Tokens40,000,000 points
GPT-5.6 Terra
Awaiting verification (UTC+8)
gpt-5.6-terraIndependent modelOpenAI · GA2026-07-09Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated73.1Value · Estimated62.5
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.0 (estimated) · 4/19 observed / reasoning 85.1 (estimated) · 4/13 observed / writing 69.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput usage · per million Tokens4,000,000 pointsCache-hit usage · per million Tokens400,000 pointsCache-write usage · per million Tokens5,000,000 pointsOutput usage · per million Tokens24,000,000 points
gpt-live-1
gpt-live-1Independent modelOpenAI · GA2026-07-08No fixed price; billed by the underlying servicePerformance · Estimated48.3Value · Estimated48.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.4 (estimated) · 0/19 observed / reasoning 52.2 (estimated) · 0/13 observed / writing 41.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: gpt-4-0125-preview · 10 benchmarksReference: gpt-4-1106-preview · 10 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4o · 7 benchmarksReference: gpt-5.2 · 7 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT Realtime 2.1
Awaiting verification (UTC+8)
gpt-realtime-2.1Independent modelOpenAI · Preview2026-07-06Realtime voice and text available. Image input and in-call tool execution are not enabled.Last price verificationAwaiting verification (UTC+8)
Performance · Estimated45.3Value · Estimated31.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · OfficialInput usage · per million Tokens8,000,000 pointsCache-hit usage · per million Tokens800,000 pointsOutput usage · per million Tokens48,000,000 pointsInput usage · Image · per million Tokens10,000,000 pointsCache-hit usage · Image · per million Tokens1,000,000 pointsInput usage · Audio · per million Tokens64,000,000 pointsCache-hit usage · Audio · per million Tokens800,000 pointsOutput usage · Audio · per million Tokens128,000,000 points
GPT Realtime 2.1 Mini
Awaiting verification (UTC+8)
gpt-realtime-2.1-miniIndependent modelOpenAI · Preview2026-07-06Realtime voice and text available. Image input and in-call tool execution are not enabled.Last price verificationAwaiting verification (UTC+8)
Performance · Estimated45.3Value · Estimated61.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · OfficialInput usage · per million Tokens1,200,000 pointsCache-hit usage · per million Tokens120,000 pointsOutput usage · per million Tokens4,800,000 pointsInput usage · Image · per million Tokens1,600,000 pointsCache-hit usage · Image · per million Tokens160,000 pointsInput usage · Audio · per million Tokens20,000,000 pointsCache-hit usage · Audio · per million Tokens600,000 pointsOutput usage · Audio · per million Tokens40,000,000 points
Qwen-Audio-3.0-TTS-Flash
Awaiting verification (UTC+8)
qwen-audio-3.0-tts-flashIndependent modelAlibaba Cloud · GA2026-07 (official month only)Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated74.4Value · Estimated74.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · OfficialAudio · per 10,000 characters273,973 points
Qwen-Audio-3.0-TTS-Plus
Awaiting verification (UTC+8)
qwen-audio-3.0-tts-plusIndependent modelAlibaba Cloud · GA2026-07 (official month only)Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated74.4Value · Estimated63.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · OfficialAudio · per 10,000 characters383,562 points
claude-sonnet-5
claude-sonnet-5Independent modelAnthropic · GA2026-06-30No fixed price; billed by the underlying servicePerformance · Estimated70.2Value · Estimated64.1
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.0 (estimated) · 5/19 observed / reasoning 76.6 (estimated) · 4/13 observed / writing 58.1 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialDynamic: router input markup plus the points for the model selected for each request.
claude-sonnet-5-100
claude-sonnet-5-100Independent modelAnthropic · GA2026-06-30No fixed price; billed by the underlying servicePerformance · Estimated70.2Value · Estimated64.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.0 (estimated) · 0/19 observed / reasoning 76.6 (estimated) · 0/13 observed / writing 58.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-sonnet-5-5-100 by 4.2 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Doubao Seed 2.1 Turbo (2026-06-28)
Awaiting verification (UTC+8)
doubao-seed-2-1-turbo-260628Fixed snapshot / version · Sole entryByteDance · GA2026-06-28Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated57.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens821,918 pointsCache-hit usage · per million Tokens164,384 pointsOutput usage · per million Tokens4,109,589 points
Mistral OCR 4
Awaiting verification (UTC+8)
mistral-ocr-4-0Independent modelMistral AI · Preview2026-06-23Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance81.8Value57.3
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 25%mistral-ocr · Officialcohere-parsebench · OfficialDocument processing · per 1,000 pages8,000,000 pointsDocument processing with structured annotations · per 1,000 pages10,000,000 points
HappyHorse-1.1-I2V
Awaiting verification (UTC+8)
happyhorse-1.1-i2vIndependent modelAlibaba Cloud · GA2026-06-22Last price verificationAwaiting verification (UTC+8)
Performance · Estimated80.9Value · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentVideo generation 480P · per second123,288 pointsVideo generation 720P · per second246,576 pointsVideo generation 1080P · per second328,768 points
HappyHorse-1.1-R2V
Awaiting verification (UTC+8)
happyhorse-1.1-r2vIndependent modelAlibaba Cloud · GA2026-06-22Last price verificationAwaiting verification (UTC+8)
Performance · Estimated80.9Value · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentVideo generation 480P · per second123,288 pointsVideo generation 720P · per second246,576 pointsVideo generation 1080P · per second328,768 points
HappyHorse-1.1-T2V
Awaiting verification (UTC+8)
happyhorse-1.1-t2vIndependent modelAlibaba Cloud · GA2026-06-22Last price verificationAwaiting verification (UTC+8)
Performance · Estimated80.9Value · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentVideo generation 480P · per second123,288 pointsVideo generation 720P · per second246,576 pointsVideo generation 1080P · per second328,768 points
doubao-GLM 5.2 (2026-06-17)
Awaiting verification (UTC+8)
doubao-glm-5-2-260617Fixed snapshot / version · Sole entryZhipu · GA2026-06-17Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated54.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens7,671,233 points
qwen-HappyOyster-1.0-Adventure
qwen-happyoyster-1.0-adventureIndependent modelhappyoyster · GA2026-06-17No fixed price; billed by the underlying servicePerformance · Estimated43.2Value · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
GLM-5.2
Awaiting verification (UTC+8)
glm-5.2Independent modelZhipu · GA2026-06-16Last price verificationAwaiting verification (UTC+8)
Performance · Estimated66.4Value · Estimated61.3
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 68.8 (estimated) · 5/19 observed / reasoning 70.9 (estimated) · 4/13 observed / writing 59.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens7,671,233 points
Qwen3.5-OCR
Awaiting verification (UTC+8)
qwen3.5-ocrIndependent modelAlibaba Cloud · GA2026-06-16Last price verificationAwaiting verification (UTC+8)
Performance · Estimated81.8Value · Estimated72.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · OfficialInput usage · per million Tokens136,987 pointsOutput usage · per million Tokens547,946 points
qwen-GLM-5.2
Awaiting verification (UTC+8)
qwen-glm-5.2Independent modelZhipu · GA2026-06-16Last price verificationAwaiting verification (UTC+8)
Performance · Estimated61.1Value · Estimated57.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens7,671,233 points
qwen-pixverse/pixverse-upscale
qwen-pixverse-pixverse-upscaleIndependent modelpixverse · GA2026-06-16No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ZHIPU/GLM-5.2
Awaiting verification (UTC+8)
qwen-zhipu-glm-5.2Independent modelZhipu AI · GA2026-06-16Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens7,671,233 points
qwen-kimi-k2.7-code
Awaiting verification (UTC+8)
qwen-kimi-k2.7-codeIndependent modelMoonshot · GA2026-06-15Last price verificationAwaiting verification (UTC+8)
Performance · Estimated34.7Value · Estimated39.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.4 (estimated) · 0/13 observed / writing 28.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,780,822 pointsCache-hit usage · per million Tokens356,164 pointsOutput usage · per million Tokens7,397,260 points
Kimi K2.7 Code
Awaiting verification (UTC+8)
kimi-k2.7-codeIndependent modelMoonshot · GA2026-06-12Last price verificationAwaiting verification (UTC+8)
Performance · Estimated46.3Value · Estimated47.8
8/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.8 (estimated) · 3/19 observed / reasoning 48.4 (estimated) · 3/13 observed / writing 42.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · IndependentInput usage · per million Tokens1,780,822 pointsCache-hit usage · per million Tokens356,164 pointsOutput usage · per million Tokens7,397,260 points
qwen-kimi/kimi-k2.7-code
Awaiting verification (UTC+8)
qwen-kimi-kimi-k2.7-codeIndependent modelMoonshot AI · GA2026-06-12Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated29.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,780,822 pointsCache-hit usage · per million Tokens356,164 pointsOutput usage · per million Tokens7,397,260 points
claude-fable-5
claude-fable-5Independent modelAnthropic · GA2026-06-09No fixed price; billed by the underlying servicePerformance · Estimated87.7Value · Estimated76.4
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.6 (estimated) · 5/19 observed / reasoning 90.7 (estimated) · 4/13 observed / writing 86.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialDynamic: router input markup plus the points for the model selected for each request.
claude-fable-5-100
claude-fable-5-100Independent modelAnthropic · GA2026-06-09No fixed price; billed by the underlying servicePerformance · Estimated87.7Value · Estimated76.4
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.6 (estimated) · 0/19 observed / reasoning 90.7 (estimated) · 0/13 observed / writing 86.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-fable-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-fable-5-1-100 by 1.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3.7-Max-2026-06-08
Awaiting verification (UTC+8)
qwen3.7-max-2026-06-08Fixed snapshot / version · Sole entryQwen · GA2026-06-09Last price verificationAwaiting verification (UTC+8)
Performance · Estimated64.5Value · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 0/19 observed / reasoning 69.6 (estimated) · 0/13 observed / writing 73.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: qwen3.7-max-preview · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens3,287,671 pointsCache-hit usage · per million Tokens657,534 pointsOutput usage · per million Tokens9,863,014 points
doubao-seedance-2-5-260628
Awaiting verification (UTC+8)
doubao-seedance-2-5-260628Fixed snapshot / version · Sole entryByteDance · GA2026-06 (official month only)Last price verificationAwaiting verification (UTC+8)
Performance · Estimated90.4Value · Estimated63.3
Version comparison reviewEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.5-720p · 90.4Review: below doubao-seedance-2-0-260128 by 1.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · IndependentOutput usage · Video generation · per million Tokens19,178,083 points
doubao-seed-evolving
doubao-seed-evolvingAlias · Sole entryDoubao · GA2026-06 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
doubao-seedream-5-0-pro-260628
Awaiting verification (UTC+8)
doubao-seedream-5-0-pro-260628Fixed snapshot / version · Sole entryByteDance · GA2026-06 (official month only)Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance · Estimated85.2Value · Estimated69.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-5.0-pro · 85.2arena · Independentarena · IndependentOutput usage · Image · per image82,192 pointsInput usage · Image · per image5,480 points
Fun-ASR-Flash-2026-06-15
Awaiting verification (UTC+8)
fun-asr-flash-2026-06-15Fixed snapshot / version · Sole entryAlibaba Cloud · GA2026-06 (official month only)Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated91.4Value · Estimated94.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · per second61 points
Qwen3.7-Plus
Awaiting verification (UTC+8)
qwen3.7-plusIndependent modelQwen · GA2026-06-01Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.0Value · Estimated60.5
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.7 (estimated) · 2/19 observed / reasoning 62.0 (estimated) · 1/13 observed / writing 55.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 256,000 TokenInput usage · per million Tokens438,356 pointsCache-hit usage · per million Tokens87,671 pointsOutput usage · per million Tokens1,753,425 points
Input 256,001+ TokenInput usage · per million Tokens1,315,068 pointsCache-hit usage · per million Tokens263,014 pointsOutput usage · per million Tokens5,260,274 points
qwen-MiniMax/MiniMax-M3
Awaiting verification (UTC+8)
qwen-minimax-minimax-m3Independent modelmini-max · GA2026-06-01Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated46.0
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-thinking-2507 · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksReview: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,150,685 pointsCache-hit usage · per million Tokens230,137 pointsOutput usage · per million Tokens4,602,740 points
qwen-stepfun/step-3.7-flash
Awaiting verification (UTC+8)
qwen-stepfun-step-3.7-flashIndependent modelstepfun · GA2026-05-29Last price verificationAwaiting verification (UTC+8)
Performance · Estimated61.4Value · Estimated64.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens369,863 pointsCache-hit usage · per million Tokens73,973 pointsOutput usage · per million Tokens2,219,178 points
claude-opus-4-8
claude-opus-4-8Independent modelAnthropic · GA2026-05-28No fixed price; billed by the underlying servicePerformance · Estimated74.3Value · Estimated67.0
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 72.3 (estimated) · 5/19 observed / reasoning 77.9 (estimated) · 4/13 observed / writing 72.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialDynamic: router input markup plus the points for the model selected for each request.
claude-opus-4-8-100
claude-opus-4-8-100Independent modelAnthropic · GA2026-05-28No fixed price; billed by the underlying servicePerformance · Estimated74.3Value · Estimated67.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 72.3 (estimated) · 0/19 observed / reasoning 77.9 (estimated) · 0/13 observed / writing 72.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-8 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3.7-Max
Awaiting verification (UTC+8)
qwen3.7-maxIndependent modelQwen · GA2026-05-21Last price verificationAwaiting verification (UTC+8)
Performance · Estimated64.5Value · Estimated58.6
8/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 3/19 observed / reasoning 69.6 (estimated) · 3/13 observed / writing 73.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max-preview · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarkslivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · IndependentInput usage · per million Tokens3,287,671 pointsCache-hit usage · per million Tokens657,534 pointsOutput usage · per million Tokens9,863,014 points
Cohere Command A Plus
Awaiting verification (UTC+8)
cohere-command-a-plus-05-2026Independent modelCohere · Preview2026-05-20Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated55.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,600,000 pointsOutput usage · per million Tokens6,400,000 points
Qwen3.7-Max-Preview
Awaiting verification (UTC+8)
qwen3.7-max-previewIndependent modelQwen · Preview2026-05-20Last price verificationAwaiting verification (UTC+8)
Performance · Estimated64.5Value · Estimated58.6
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 1/19 observed / reasoning 69.6 (estimated) · 1/13 observed / writing 73.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens3,287,671 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens9,863,014 points
Qwen3.5-LiveTranslate-Flash-Realtime
qwen3.5-livetranslate-flash-realtimeIndependent modelQwen · GA2026-05-19No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Grok 4.3
Awaiting verification (UTC+8)
grok-4.3Independent modelxAI · Preview2026-05-12Last price verificationAwaiting verification (UTC+8)
Performance · Estimated44.8Value · Estimated46.5
Shared exact-model performance from grok-4.3; coverage refers to public model benchmarks, not tests of every platform deployment.12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.8 (estimated) · 4/19 observed / reasoning 48.3 (estimated) · 4/13 observed / writing 47.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput usage · per million Tokens2,500,000 pointsCache-hit usage · per million Tokens400,000 pointsOutput usage · per million Tokens5,000,000 points
Mistral Medium 3.5
Awaiting verification (UTC+8)
mistral-medium-3-5Independent modelMistral AI · Preview2026-04-28Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated60.6Value · Estimated55.3
6/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 3/19 observed / reasoning 70.3 (estimated) · 1/13 observed / writing 61.1 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independentarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officiallivebench · IndependentInput usage · per million Tokens3,000,000 pointsOutput usage · per million Tokens15,000,000 points
HappyHorse-1.0-I2V
Awaiting verification (UTC+8)
happyhorse-1.0-i2vIndependent modelAlibaba Cloud · GA2026-04-27Last price verificationAwaiting verification (UTC+8)
Performance · Estimated80.9Value · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentVideo generation 720P · per second246,576 pointsVideo generation 1080P · per second438,357 points
HappyHorse-1.0-R2V
Awaiting verification (UTC+8)
happyhorse-1.0-r2vIndependent modelAlibaba Cloud · GA2026-04-27Last price verificationAwaiting verification (UTC+8)
Performance · Estimated80.9Value · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentVideo generation 720P · per second246,576 pointsVideo generation 1080P · per second438,357 points
HappyHorse-1.0-T2V
Awaiting verification (UTC+8)
happyhorse-1.0-t2vIndependent modelAlibaba Cloud · GA2026-04-27Last price verificationAwaiting verification (UTC+8)
Performance · Estimated80.9Value · Estimated56.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · IndependentVideo generation 720P · per second246,576 pointsVideo generation 1080P · per second438,357 points
qwen-DeepSeek-V4-Pro
Awaiting verification (UTC+8)
qwen-deepseek-v4-proIndependent modelDeepSeek · GA2026-04-24Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated70.1Value · Estimated63.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.8 (estimated) · 0/19 observed / reasoning 74.5 (estimated) · 0/13 observed / writing 69.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-27b · 13 benchmarksReference: qwen3.8-max · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens3,287,671 pointsCache-hit usage · per million Tokens273,973 pointsOutput usage · per million Tokens6,575,342 points
GPT-5.5
Awaiting verification (UTC+8)
gpt-5.5Independent modelOpenAI · GA2026-04-23Last price verificationAwaiting verification (UTC+8)
Performance · Estimated80.5Value · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 71.8 (estimated) · 4/19 observed / reasoning 88.6 (estimated) · 4/13 observed / writing 81.1 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.5 (codex-harness) · 1 benchmarksReference: gpt-5.5-high (codex-harness) · 1 benchmarksReference: gpt-5.5-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput usage · per million Tokens10,000,000 pointsCache-hit usage · per million Tokens1,000,000 pointsOutput usage · per million Tokens60,000,000 points
qwen-xiaomi/mimo-v2.5-pro
Awaiting verification (UTC+8)
qwen-xiaomi-mimo-v2.5-proIndependent modelXiaomi · GA2026-04-23Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated30.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,917,808 pointsCache-hit usage · per million Tokens383,562 pointsOutput usage · per million Tokens5,753,425 points
Qwen3.6-27B
Awaiting verification (UTC+8)
qwen3.6-27bIndependent modelQwen · GA2026-04-22Last price verificationAwaiting verification (UTC+8)
Performance · Estimated46.6Value · Estimated50.5
7/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 40.1 (estimated) · 2/19 observed / reasoning 56.9 (estimated) · 3/13 observed / writing 42.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.5-122b-a10b · 5 benchmarksReference: qwen3.5-27b · 5 benchmarksReference: qwen3.5-397b-a17b · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarkslivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · IndependentInput usage · per million Tokens821,918 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens4,931,507 points
GPT Image 2
Awaiting verification (UTC+8)
gpt-image-2Independent modelOpenAI · GA2026-04-21Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance97.0Value69.3
Input usage · per million Tokens10,000,000 pointsCache-hit usage · per million Tokens2,500,000 pointsInput usage · Image · per million Tokens16,000,000 pointsCache-hit usage · Image · per million Tokens4,000,000 pointsOutput usage · Image · per million Tokens60,000,000 points
qwen-Kimi-K2.6
Awaiting verification (UTC+8)
qwen-kimi-k2.6Independent modelMoonshot · GA2026-04-21Last price verificationAwaiting verification (UTC+8)
Performance · Estimated34.9Value · Estimated39.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,780,822 pointsCache-hit usage · per million Tokens356,164 pointsOutput usage · per million Tokens7,397,260 points
Kimi K2.6
Awaiting verification (UTC+8)
kimi-k2.6Independent modelMoonshot · GA2026-04-20Last price verificationAwaiting verification (UTC+8)
Performance · Estimated77.4Value · Estimated69.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 77.8 (estimated) · 2/19 observed / reasoning 78.7 (estimated) · 1/13 observed / writing 75.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: kimi-k3 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput usage · per million Tokens1,780,822 pointsCache-hit usage · per million Tokens301,370 pointsOutput usage · per million Tokens7,397,260 points
qwen-Kimi/Kimi K2.6
Awaiting verification (UTC+8)
qwen-kimi-kimi-k2.6Independent modelMoonshot AI · GA2026-04-20Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,780,822 pointsCache-hit usage · per million Tokens301,370 pointsOutput usage · per million Tokens7,397,260 points
claude-opus-4-7
claude-opus-4-7Independent modelAnthropic · GA2026-04-16No fixed price; billed by the underlying servicePerformance · Estimated74.1Value · Estimated66.9
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.6 (estimated) · 4/19 observed / reasoning 81.7 (estimated) · 4/13 observed / writing 67.0 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
claude-opus-4-7-100
claude-opus-4-7-100Independent modelAnthropic · GA2026-04-16No fixed price; billed by the underlying servicePerformance · Estimated74.1Value · Estimated66.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.6 (estimated) · 0/19 observed / reasoning 81.7 (estimated) · 0/13 observed / writing 67.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-7 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3.6-35B-A3B
Awaiting verification (UTC+8)
qwen3.6-35b-a3bIndependent modelQwen · GA2026-04-16Last price verificationAwaiting verification (UTC+8)
Performance · Estimated45.4Value · Estimated51.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.0 (estimated) · 0/19 observed / reasoning 54.8 (estimated) · 0/13 observed / writing 42.3 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.5-122b-a10b · 5 benchmarksReference: qwen3.5-35b-a3b · 5 benchmarksReference: qwen3.5-397b-a17b · 5 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens493,151 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens2,958,904 points
Qwen3.6-Flash
Awaiting verification (UTC+8)
qwen3.6-flashIndependent modelQwen · GA2026-04-16Last price verificationAwaiting verification (UTC+8)
Performance · Estimated58.2Value · Estimated62.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 256,000 TokenInput usage · per million Tokens328,767 pointsCache-hit usage · per million Tokens65,753 pointsOutput usage · per million Tokens1,972,603 points
Input 256,001+ TokenInput usage · per million Tokens1,315,068 pointsCache-hit usage · per million Tokens263,014 pointsOutput usage · per million Tokens7,890,411 points
qwen-GLM-5.1
Awaiting verification (UTC+8)
qwen-glm-5.1Independent modelZhipu · GA2026-04-14Last price verificationAwaiting verification (UTC+8)
Performance · Estimated61.1Value · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32,000 TokenInput usage · per million Tokens1,643,836 pointsCache-hit usage · per million Tokens328,767 pointsOutput usage · per million Tokens6,575,342 points
Input 32,001+ TokenInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens438,356 pointsOutput usage · per million Tokens7,671,233 points
qwen-ViduQ3-mix_reference2video
qwen-vidu-viduq3-mix_reference2videoIndependent modelvidu · GA2026-04-13No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3_reference2video
qwen-vidu-viduq3_reference2videoIndependent modelvidu · GA2026-04-13No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-Turbo_reference2video
qwen-vidu-viduq3-turbo_reference2videoIndependent modelvidu · GA2026-04-13No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-PixVerse-C1-it2v
qwen-pixverse-pixverse-c1-it2vIndependent modelpixverse · GA2026-04-07No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-PixVerse-C1-kf2v
qwen-pixverse-pixverse-c1-kf2vIndependent modelpixverse · GA2026-04-07No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-PixVerse-C1-r2v
qwen-pixverse-pixverse-c1-r2vIndependent modelpixverse · GA2026-04-07No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-PixVerse-C1-t2v
qwen-pixverse-pixverse-c1-t2vIndependent modelpixverse · GA2026-04-07No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ZHIPU/GLM-5.1
Awaiting verification (UTC+8)
qwen-zhipu-glm-5.1Independent modelZhipu AI · GA2026-04-07Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens7,671,233 points
Wan2.7-I2V
Awaiting verification (UTC+8)
wan2.7-i2vIndependent modelAlibaba Cloud · GA2026-04-07Last price verificationAwaiting verification (UTC+8)
Performance78.7Value63.2
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentVideo generation 720P · per second164,384 pointsVideo generation 1080P · per second273,973 points
Wan2.7-R2V
Awaiting verification (UTC+8)
wan2.7-r2vIndependent modelAlibaba Cloud · GA2026-04-07Last price verificationAwaiting verification (UTC+8)
Performance · Estimated69.2Value · Estimated56.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-i2v · 78.7Reference: wan2.7-t2v · 59.6arena · Independentarena · IndependentVideo generation 720P · per second164,384 pointsVideo generation 1080P · per second273,973 points
Wan2.7-T2V
Awaiting verification (UTC+8)
wan2.7-t2vIndependent modelAlibaba Cloud · GA2026-04-07Last price verificationAwaiting verification (UTC+8)
Performance59.6Value49.8
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentVideo generation 720P · per second164,384 pointsVideo generation 1080P · per second273,973 points
qwen-Wan2.7-VideoEdit
wan2.7-videoeditIndependent modelWan · GA2026-04-07No fixed price; billed by the underlying servicePerformance · Estimated69.2Value · Estimated63.4
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-i2v · 78.7Reference: wan2.7-t2v · 59.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Grok 4.20 Non-Reasoning
Awaiting verification (UTC+8)
grok-4-20-non-reasoningIndependent modelxAI · Preview2026-04-06Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated54.7
Shared exact-model performance from grok-4-20-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,500,000 pointsCache-hit usage · per million Tokens400,000 pointsOutput usage · per million Tokens5,000,000 points
Grok 4.20 Reasoning
Awaiting verification (UTC+8)
grok-4-20-reasoningIndependent modelxAI · Preview2026-04-06Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated54.7
Shared exact-model performance from grok-4-20-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,500,000 pointsCache-hit usage · per million Tokens400,000 pointsOutput usage · per million Tokens5,000,000 points
Gemma 4 26B A4B It-100
Awaiting verification (UTC+8)
gemma-4-26b-a4b-it-maas-001Independent modelGoogle · Preview2026-04-02Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated62.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens300,000 pointsCache-hit usage · per million Tokens30,000 pointsOutput usage · per million Tokens1,200,000 points
Veo 3.1 Lite Generate 001-100
veo-3.1-lite-generate-001Independent modelGoogle · GA2026-04-02No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
doubao-seed3d-2-0-260328
Awaiting verification (UTC+8)
doubao-seed3d-2-0-260328Fixed snapshot / version · Sole entryByteDance · GA2026-04 (official month only)Last price verificationAwaiting verification (UTC+8)
Performance82.2Value57.5
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 18%seed3d-public · OfficialOutput usage · 3D · per million Tokens21,917,809 points
Qwen3.6-Plus
Awaiting verification (UTC+8)
qwen3.6-plusIndependent modelQwen · GA2026-04-01Last price verificationAwaiting verification (UTC+8)
Performance · Estimated54.5Value · Estimated57.7
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 4/19 observed / reasoning 60.4 (estimated) · 4/13 observed / writing 52.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput 0 – 256,000 TokenInput usage · per million Tokens547,945 pointsCache-hit usage · per million Tokens109,589 pointsOutput usage · per million Tokens3,287,671 points
Input 256,001+ TokenInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens438,356 pointsOutput usage · per million Tokens13,150,685 points
Wan2.7-Image
Awaiting verification (UTC+8)
wan2.7-imageIndependent modelAlibaba Cloud · GA2026-04-01Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance41.7Value46.3
Version comparison reviewProvisional
2026-10-08 16:22 (UTC+8) · Confidence 45%Review: below wan2.6-t2i by 8.3 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · IndependentOutput usage · Image · per image54,795 points
Wan2.7-Image-Pro
Awaiting verification (UTC+8)
wan2.7-image-proIndependent modelAlibaba Cloud · GA2026-04-01Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance44.1Value30.9
Output usage · Image · per image136,987 points
qwen-PixVerse-V6-it2v
qwen-pixverse-pixverse-v6-it2vIndependent modelpixverse · GA2026-03-29No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-PixVerse-V6-kf2v
qwen-pixverse-pixverse-v6-kf2vIndependent modelpixverse · GA2026-03-29No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-PixVerse-V6-t2v
qwen-pixverse-pixverse-v6-t2vIndependent modelpixverse · GA2026-03-29No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
GLM-5.1
Awaiting verification (UTC+8)
glm-5.1Independent modelZhipu · GA2026-03-27Last price verificationAwaiting verification (UTC+8)
Performance · Estimated65.1Value · Estimated61.4
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.7 (estimated) · 2/19 observed / reasoning 69.9 (estimated) · 1/13 observed / writing 58.6 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 31,999 TokenInput usage · per million Tokens1,643,836 pointsCache-hit usage · per million Tokens356,164 pointsOutput usage · per million Tokens6,575,342 points
Input 32,000+ TokenInput usage · per million Tokens2,191,781 pointsCache-hit usage · per million Tokens547,945 pointsOutput usage · per million Tokens7,671,233 points
Lyria 3 Clip Preview-100
lyria-3-clip-previewIndependent modelGoogle · GA2026-03-25No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Lyria 3 Pro Preview-100
lyria-3-pro-previewIndependent modelGoogle · GA2026-03-25No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-MiniMax/MiniMax-M2.7
Awaiting verification (UTC+8)
qwen-minimax-minimax-m2.7Independent modelMiniMax · GA2026-03-18Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens575,342 pointsCache-hit usage · per million Tokens115,068 pointsOutput usage · per million Tokens2,301,370 points
GPT-5.4 Mini
Awaiting verification (UTC+8)
gpt-5.4-miniIndependent modelOpenAI · GA2026-03-17Last price verificationAwaiting verification (UTC+8)
Performance · Estimated47.9Value · Estimated48.9
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 44.3 (estimated) · 4/19 observed / reasoning 53.8 (estimated) · 4/13 observed / writing 45.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput usage · per million Tokens1,500,000 pointsCache-hit usage · per million Tokens150,000 pointsOutput usage · per million Tokens9,000,000 points
GPT-5.4 Nano
Awaiting verification (UTC+8)
gpt-5.4-nanoIndependent modelOpenAI · GA2026-03-17Last price verificationAwaiting verification (UTC+8)
Performance · Estimated48.6Value · Estimated54.8
11/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 44.5 (estimated) · 3/19 observed / reasoning 57.0 (estimated) · 4/13 observed / writing 44.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-nano-2025-04-14 · 7 benchmarksReference: gpt-5.4 · 2 benchmarksReference: gpt-5.4-high (codex-harness) · 1 benchmarksReference: gpt-5.4-mini · 1 benchmarksarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · IndependentInput usage · per million Tokens400,000 pointsCache-hit usage · per million Tokens40,000 pointsOutput usage · per million Tokens2,500,000 points
GLM-5-Turbo
Awaiting verification (UTC+8)
glm-5-turboIndependent modelZhipu · GA2026-03-14Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated56.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 31,999 TokenInput usage · per million Tokens1,369,863 pointsCache-hit usage · per million Tokens328,767 pointsOutput usage · per million Tokens6,027,397 points
Input 32,000+ TokenInput usage · per million Tokens1,917,808 pointsCache-hit usage · per million Tokens493,151 pointsOutput usage · per million Tokens7,123,288 points
qwen-Tripo-P1.0
qwen-tripo-tripo-p1.0Independent modeltripo · GA2026-03-11No fixed price; billed by the underlying servicePerformance · Estimated43.2Value · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Tripo-H3.1
qwen-tripo-tripo-h3.1Independent modeltripo · GA2026-03-06No fixed price; billed by the underlying servicePerformance · Estimated44.9Value · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT-5.4
Awaiting verification (UTC+8)
gpt-5.4Independent modelOpenAI · GA2026-03-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated73.0Value · Estimated61.5
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.7 (estimated) · 5/19 observed / reasoning 84.9 (estimated) · 4/13 observed / writing 75.5 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · OfficialInput usage · per million Tokens5,000,000 pointsCache-hit usage · per million Tokens500,000 pointsOutput usage · per million Tokens30,000,000 points
GPT-5.4 Pro
Awaiting verification (UTC+8)
gpt-5.4-proIndependent modelOpenAI · GA2026-03-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated58.8Value · Estimated41.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 49.8 (estimated) · 0/19 observed / reasoning 67.8 (estimated) · 0/13 observed / writing 58.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-5.4 · 13 benchmarksReference: gpt-5.4-mini · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: gpt-5.4-nano · 11 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens60,000,000 pointsOutput usage · per million Tokens360,000,000 points
Qwen3.5-Omni-Flash
qwen3.5-omni-flashIndependent modelQwen · GA2026-03 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated58.2Value · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3.5-Omni-Flash-Realtime
qwen3.5-omni-flash-realtimeIndependent modelQwen · GA2026-03 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Qwen3.5-Omni-Plus
qwen3.5-omni-plusIndependent modelQwen · GA2026-03 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated54.5Value · Estimated53.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 0/19 observed / reasoning 60.4 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3.5-Omni-Plus-Realtime
qwen3.5-omni-plus-realtimeIndependent modelQwen · GA2026-03 (official month only)No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
qwen-pixverse/pixverse-motioncontrol
qwen-pixverse-pixverse-motioncontrolIndependent modelpixverse · GA2026-02-28No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT-5.3 Codex
Awaiting verification (UTC+8)
gpt-5.3-codexIndependent modelOpenAI · GA2026-02-24Last price verificationAwaiting verification (UTC+8)
Performance · Estimated58.5Value · Estimated52.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.4 (estimated) · 0/19 observed / reasoning 63.1 (estimated) · 0/13 observed / writing 56.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-5.4 · 9 benchmarksReference: gpt-5.2 · 8 benchmarksReference: gpt-5.2-codex · 8 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.2-codex by 3.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens3,500,000 pointsCache-hit usage · per million Tokens350,000 pointsOutput usage · per million Tokens28,000,000 points
qwen-MiniMax-M2.5
Awaiting verification (UTC+8)
qwen-minimax-m2.5Independent modelMiniMax · GA2026-02-24Last price verificationAwaiting verification (UTC+8)
Performance · Estimated34.9Value · Estimated44.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens575,342 pointsCache-hit usage · per million Tokens115,068 pointsOutput usage · per million Tokens2,301,370 points
GPT Audio 1.5
Awaiting verification (UTC+8)
gpt-audio-1.5Independent modelOpenAI · GA2026-02-23Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated52.6Value · Estimated41.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · OfficialInput usage · per million Tokens5,000,000 pointsOutput usage · per million Tokens20,000,000 pointsInput usage · Audio · per million Tokens64,000,000 pointsOutput usage · Audio · per million Tokens128,000,000 points
GPT Realtime 1.5
Awaiting verification (UTC+8)
gpt-realtime-1.5Independent modelOpenAI · GA2026-02-23Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated45.3Value · Estimated31.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · OfficialInput usage · per million Tokens8,000,000 pointsCache-hit usage · per million Tokens800,000 pointsOutput usage · per million Tokens32,000,000 pointsInput usage · Image · per million Tokens10,000,000 pointsCache-hit usage · Image · per million Tokens1,000,000 pointsInput usage · Audio · per million Tokens64,000,000 pointsCache-hit usage · Audio · per million Tokens800,000 pointsOutput usage · Audio · per million Tokens128,000,000 points
Qwen3.5-122B-A10B
Awaiting verification (UTC+8)
qwen3.5-122b-a10bIndependent modelQwen · GA2026-02-23Last price verificationAwaiting verification (UTC+8)
Performance · Estimated46.4Value · Estimated55.2
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.9 (estimated) · 2/19 observed / reasoning 56.8 (estimated) · 1/13 observed / writing 42.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128,000 TokenInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens1,753,425 points
Input 128,001+ TokenInput usage · per million Tokens547,945 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens4,383,562 points
Qwen3.5-27B
Awaiting verification (UTC+8)
qwen3.5-27bIndependent modelQwen · GA2026-02-23Last price verificationAwaiting verification (UTC+8)
Performance · Estimated45.7Value · Estimated55.9
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.4 (estimated) · 2/19 observed / reasoning 56.1 (estimated) · 1/13 observed / writing 41.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128,000 TokenInput usage · per million Tokens164,384 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens1,315,068 points
Input 128,001+ TokenInput usage · per million Tokens493,151 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens3,945,205 points
Qwen3.5-35B-A3B
Awaiting verification (UTC+8)
qwen3.5-35b-a3bIndependent modelQwen · GA2026-02-23Last price verificationAwaiting verification (UTC+8)
Performance · Estimated42.9Value · Estimated55.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.8 (estimated) · 2/19 observed / reasoning 51.7 (estimated) · 1/13 observed / writing 40.2 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128,000 TokenInput usage · per million Tokens109,589 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens876,712 points
Input 128,001+ TokenInput usage · per million Tokens438,356 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens3,506,849 points
Qwen3.5-Flash
Awaiting verification (UTC+8)
qwen3.5-flashIndependent modelQwen · GA2026-02-23Last price verificationAwaiting verification (UTC+8)
Performance · Estimated58.2Value · Estimated68.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 2/19 observed / reasoning 62.8 (estimated) · 1/13 observed / writing 59.9 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128,000 TokenInput usage · per million Tokens54,795 pointsCache-hit usage · per million Tokens10,959 pointsOutput usage · per million Tokens547,945 points
Input 128,001 – 256,000 TokenInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens43,836 pointsOutput usage · per million Tokens2,191,781 points
Input 256,001+ TokenInput usage · per million Tokens328,767 pointsCache-hit usage · per million Tokens65,753 pointsOutput usage · per million Tokens3,287,671 points
qwen-GLM-5
Awaiting verification (UTC+8)
qwen-glm-5Independent modelZhipu · GA2026-02-18Last price verificationAwaiting verification (UTC+8)
Performance · Estimated61.1Value · Estimated60.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32,000 TokenInput usage · per million Tokens1,095,890 pointsCache-hit usage · per million Tokens219,178 pointsOutput usage · per million Tokens4,931,507 points
Input 32,001+ TokenInput usage · per million Tokens1,643,836 pointsCache-hit usage · per million Tokens328,767 pointsOutput usage · per million Tokens6,027,397 points
claude-sonnet-4-6
claude-sonnet-4-6Independent modelAnthropic · GA2026-02-17No fixed price; billed by the underlying servicePerformance · Estimated65.2Value · Estimated60.6
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.0 (estimated) · 4/19 observed / reasoning 71.9 (estimated) · 4/13 observed / writing 59.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
claude-sonnet-4-6-100
claude-sonnet-4-6-100Independent modelAnthropic · GA2026-02-17No fixed price; billed by the underlying servicePerformance · Estimated65.2Value · Estimated60.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.0 (estimated) · 0/19 observed / reasoning 71.9 (estimated) · 0/13 observed / writing 59.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-4-6 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3.5-397B-A17B
Awaiting verification (UTC+8)
qwen3.5-397b-a17bIndependent modelQwen · GA2026-02-15Last price verificationAwaiting verification (UTC+8)
Performance · Estimated49.6Value · Estimated56.4
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 42.6 (estimated) · 2/19 observed / reasoning 59.5 (estimated) · 1/13 observed / writing 46.6 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 128,000 TokenInput usage · per million Tokens328,767 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens1,972,603 points
Input 128,001+ TokenInput usage · per million Tokens821,918 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens4,931,507 points
Qwen3.5-Plus
Awaiting verification (UTC+8)
qwen3.5-plusIndependent modelQwen · GA2026-02-15Last price verificationAwaiting verification (UTC+8)
Performance · Estimated54.5Value · Estimated61.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 0/19 observed / reasoning 60.4 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 128,000 TokenInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens43,836 pointsOutput usage · per million Tokens1,315,068 points
Input 128,001 – 256,000 TokenInput usage · per million Tokens547,945 pointsCache-hit usage · per million Tokens109,589 pointsOutput usage · per million Tokens3,287,671 points
Input 256,001+ TokenInput usage · per million Tokens1,095,890 pointsCache-hit usage · per million Tokens219,178 pointsOutput usage · per million Tokens6,575,342 points
qwen-MiniMax/MiniMax-M2.5
Awaiting verification (UTC+8)
qwen-minimax-minimax-m2.5Independent modelMiniMax · GA2026-02-12Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens575,342 pointsCache-hit usage · per million Tokens57,534 pointsOutput usage · per million Tokens2,301,370 points
qwen-PixVerse-V5.6-r2v
qwen-pixverse-pixverse-v5.6-r2vIndependent modelpixverse · GA2026-02-12No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ZHIPU/GLM-5
Awaiting verification (UTC+8)
qwen-zhipu-glm-5Independent modelZhipu AI · GA2026-02-12Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated31.2
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,643,836 pointsCache-hit usage · per million Tokens410,959 pointsOutput usage · per million Tokens6,027,397 points
qwen-ViduQ3-Pro_start-end2video
qwen-vidu-viduq3-pro_start-end2videoIndependent modelvidu · GA2026-02-11No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-Turbo_img2video
qwen-vidu-viduq3-turbo_img2videoIndependent modelvidu · GA2026-02-11No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-Turbo_start-end2video
qwen-vidu-viduq3-turbo_start-end2videoIndependent modelvidu · GA2026-02-11No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-Turbo_text2video
qwen-vidu-viduq3-turbo_text2videoIndependent modelvidu · GA2026-02-11No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
GLM-5
Awaiting verification (UTC+8)
glm-5Independent modelZhipu · GA2026-02-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated62.3Value · Estimated60.9
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.4 (estimated) · 2/19 observed / reasoning 66.5 (estimated) · 1/13 observed / writing 56.9 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 31,999 TokenInput usage · per million Tokens1,095,890 pointsCache-hit usage · per million Tokens273,973 pointsOutput usage · per million Tokens4,931,507 points
Input 32,000+ TokenInput usage · per million Tokens1,643,836 pointsCache-hit usage · per million Tokens410,959 pointsOutput usage · per million Tokens6,027,397 points
Qwen-Image-2.0
Awaiting verification (UTC+8)
qwen-image-2.0Independent modelAlibaba Cloud · GA2026-02-10Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance · Estimated73.8Value · Estimated68.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8arena · Independentarena · IndependentOutput usage · Image · per image54,795 points
claude-opus-4-6
claude-opus-4-6Independent modelAnthropic · GA2026-02-05No fixed price; billed by the underlying servicePerformance · Estimated70.8Value · Estimated64.6
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.4 (estimated) · 4/19 observed / reasoning 75.9 (estimated) · 4/13 observed / writing 70.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
claude-opus-4-6-100
claude-opus-4-6-100Independent modelAnthropic · GA2026-02-05No fixed price; billed by the underlying servicePerformance · Estimated70.8Value · Estimated64.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.4 (estimated) · 0/19 observed / reasoning 75.9 (estimated) · 0/13 observed / writing 70.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-6 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Kling Image 3.0
qwen-kling-kling-v3-image-generationIndependent modelkling · GA2026-02-05No fixed price; billed by the underlying servicePerformance · Estimated73.8Value · Estimated66.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Kling Image 3.0 Omni
qwen-kling-kling-v3-omni-image-generationIndependent modelkling · GA2026-02-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Kling Video 3.0 Omni
qwen-kling-kling-v3-omni-video-generationIndependent modelkling · GA2026-02-05No fixed price; billed by the underlying servicePerformance · Estimated41.7Value · Estimated44.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.7 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 37.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-vl-235b-a22b-instruct · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Kling Video 3.0
qwen-kling-kling-v3-video-generationIndependent modelkling · GA2026-02-05No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Kimi-K2.5
Awaiting verification (UTC+8)
qwen-kimi-k2.5Independent modelMoonshot · GA2026-01-30Last price verificationAwaiting verification (UTC+8)
Performance · Estimated34.9Value · Estimated41.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,095,890 pointsCache-hit usage · per million Tokens219,178 pointsOutput usage · per million Tokens5,753,425 points
Fun-ASR-Flash-8k实时语音识别
fun-asr-flash-8k-realtimeIndependent modelQwen · GA2026-01-28No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ2-Pro_reference2video
qwen-vidu-viduq2-pro_reference2videoIndependent modelvidu · GA2026-01-27No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-Pro_img2video
qwen-vidu-viduq3-pro_img2videoIndependent modelvidu · GA2026-01-27No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-Pro_text2video
qwen-vidu-viduq3-pro_text2videoIndependent modelvidu · GA2026-01-27No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3-VL-Plus
Awaiting verification (UTC+8)
qwen3-vl-plusIndependent modelQwen · GA2026-01-26Last price verificationAwaiting verification (UTC+8)
Performance · Estimated42.7Value · Estimated51.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.3 (estimated) · 0/19 observed / reasoning 44.7 (estimated) · 0/13 observed / writing 38.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32,000 TokenInput usage · per million Tokens273,973 pointsCache-hit usage · per million Tokens54,795 pointsOutput usage · per million Tokens2,739,726 points
Input 32,001 – 128,000 TokenInput usage · per million Tokens410,959 pointsCache-hit usage · per million Tokens82,192 pointsOutput usage · per million Tokens4,109,589 points
Input 128,001+ TokenInput usage · per million Tokens821,918 pointsCache-hit usage · per million Tokens164,384 pointsOutput usage · per million Tokens8,219,178 points
qwen-PixVerse-V5.6-it2v
qwen-pixverse-pixverse-v5.6-it2vIndependent modelpixverse · GA2026-01-26No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-PixVerse-V5.6-kf2v
qwen-pixverse-pixverse-v5.6-kf2vIndependent modelpixverse · GA2026-01-26No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-PixVerse-V5.6-t2v
qwen-pixverse-pixverse-v5.6-t2vIndependent modelpixverse · GA2026-01-26No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Virtual Try On 001-100
virtual-try-on-001Independent modelGoogle · GA2026-01-23No fixed price; billed by the underlying servicePerformance · Estimated44.5Value · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT-5.2 Codex
Awaiting verification (UTC+8)
gpt-5.2-codexIndependent modelOpenAI · GA2026-01-14Last price verificationAwaiting verification (UTC+8)
Performance · Estimated62.0Value · Estimated54.5
Version comparison review8/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 59.8 (estimated) · 3/19 observed / reasoning 68.2 (estimated) · 3/13 observed / writing 58.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 4 benchmarksReference: gpt-5.2-chat-latest-20260210 · 4 benchmarksReference: gpt-5.4 · 1 benchmarksReview: below gpt-5.1-codex by 1.6 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · IndependentInput usage · per million Tokens3,500,000 pointsCache-hit usage · per million Tokens350,000 pointsOutput usage · per million Tokens28,000,000 points
qwen-MiniMax/MiniMax-M2.1
Awaiting verification (UTC+8)
qwen-minimax-minimax-m2.1Independent modelMiniMax · GA2025-12-23Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens575,342 pointsCache-hit usage · per million Tokens57,534 pointsOutput usage · per million Tokens2,301,370 points
GLM-4.7
Awaiting verification (UTC+8)
glm-4.7Independent modelZhipu · GA2025-12-22Last price verificationAwaiting verification (UTC+8)
Performance · Estimated60.2Value · Estimated60.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.3 (estimated) · 2/19 observed / reasoning 63.5 (estimated) · 1/13 observed / writing 53.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput 0 – 31,999 Token · Output 0 – 199 TokenInput usage · per million Tokens547,945 pointsCache-hit usage · per million Tokens109,589 pointsOutput usage · per million Tokens2,191,781 points
Input 0 – 31,999 Token · Output 200+ TokenInput usage · per million Tokens821,918 pointsCache-hit usage · per million Tokens164,384 pointsOutput usage · per million Tokens3,835,616 points
Input 32,000+ TokenInput usage · per million Tokens1,095,890 pointsCache-hit usage · per million Tokens219,178 pointsOutput usage · per million Tokens4,383,562 points
GPT Image 1.5
Awaiting verification (UTC+8)
gpt-image-1.5Independent modelOpenAI · GA2025-12-16Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance76.0Value53.2
Input usage · per million Tokens10,000,000 pointsCache-hit usage · per million Tokens2,500,000 pointsInput usage · Image · per million Tokens16,000,000 pointsCache-hit usage · Image · per million Tokens4,000,000 pointsOutput usage · per million Tokens20,000,000 pointsOutput usage · Image · per million Tokens64,000,000 points
Wan2.6-I2V
Awaiting verification (UTC+8)
wan2.6-i2vIndependent modelAlibaba Cloud · GA2025-12-16Last price verificationAwaiting verification (UTC+8)
Performance53.2Value45.3
Version comparison reviewProvisional
2026-10-08 16:22 (UTC+8) · Confidence 45%Review: below wan2.5-i2v-preview by 2.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · IndependentVideo generation 720P · per second164,384 pointsVideo generation 1080P · per second273,973 points
Wan2.6-Image
Awaiting verification (UTC+8)
wan2.6-imageIndependent modelAlibaba Cloud · GA2025-12-16Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance31.6Value39.2
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentOutput usage · Image · per image54,795 points
qwen-Wan2.6-R2V
wan2.6-r2vIndependent modelWan · GA2025-12-16No fixed price; billed by the underlying servicePerformance · Estimated55.3Value · Estimated53.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Wan2.6-T2I
Awaiting verification (UTC+8)
wan2.6-t2iIndependent modelAlibaba Cloud · GA2025-12-16Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance50.0Value52.1
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentOutput usage · Image · per image54,795 points
Wan2.6-T2V
Awaiting verification (UTC+8)
wan2.6-t2vIndependent modelAlibaba Cloud · GA2025-12-16Last price verificationAwaiting verification (UTC+8)
Performance57.4Value48.3
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentVideo generation 720P · per second164,384 pointsVideo generation 1080P · per second273,973 points
Cohere Rerank v4.0 Pro
Awaiting verification (UTC+8)
cohere-rerank-v4.0-proIndependent modelCohere · GA2025-12-11Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated65.8Value · Estimated61.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-0.6B · 68.8Reference: gte-multilingual-reranker-base · 62.7Reference: BGE-reranker-v2-m3 · 57.7qwen-rerank-public · OfficialReranking · per 1,000 search units5,000,000 points
GPT-5.2
Awaiting verification (UTC+8)
gpt-5.2Independent modelOpenAI · GA2025-12-11Last price verificationAwaiting verification (UTC+8)
Performance · Estimated61.7Value · Estimated54.3
Version comparison review12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 52.5 (estimated) · 4/19 observed / reasoning 73.8 (estimated) · 4/13 observed / writing 58.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.4 · 1 benchmarksReview: below gpt-5.1 by 2.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentInput usage · per million Tokens3,500,000 pointsCache-hit usage · per million Tokens350,000 pointsOutput usage · per million Tokens28,000,000 points
GPT-5.1 Codex Max
Awaiting verification (UTC+8)
gpt-5.1-codex-maxIndependent modelOpenAI · GA2025-12-04Last price verificationAwaiting verification (UTC+8)
Performance · Estimated72.5Value · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 69.3 (estimated) · 0/19 observed / reasoning 78.4 (estimated) · 0/13 observed / writing 69.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-6-sol-max · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.4 · 1 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,500,000 pointsCache-hit usage · per million Tokens250,000 pointsOutput usage · per million Tokens20,000,000 points
Mistral Large 3
Awaiting verification (UTC+8)
mistral-large-3Independent modelMistral AI · GA2025-12-02Last price verificationAwaiting verification (UTC+8)
Performance · Estimated60.6Value · Estimated60.8
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.7 (estimated) · 2/19 observed / reasoning 66.7 (estimated) · 1/13 observed / writing 60.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput usage · per million Tokens1,000,000 pointsOutput usage · per million Tokens3,000,000 points
qwen-ViduQ2-Pro-fast_img2video
qwen-vidu-viduq2-pro-fast_img2videoIndependent modelvidu · GA2025-12-02No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3-LiveTranslate-Flash
qwen3-livetranslate-flashIndependent modelQwen · GA2025-12-01No fixed price; billed by the underlying servicePerformance · Estimated58.2Value · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3-Omni-Flash
qwen3-omni-flashIndependent modelQwen · GA2025-12-01No fixed price; billed by the underlying servicePerformance · Estimated58.2Value · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-SiliconFlow DeepSeek-V3.2
qwen-siliconflow-deepseek-v3.2Independent modelDeepSeek · GA2025-12-01No fixed price; billed by the underlying servicePerformance · Estimated45.8Value · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.1 (estimated) · 0/19 observed / reasoning 54.2 (estimated) · 0/13 observed / writing 45.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.2-exp · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Vanchin/DeepSeek-V3.2-think
qwen-vanchin-deepseek-v3.2-thinkIndependent modelDeepSeek · GA2025-12-01No fixed price; billed by the underlying servicePerformance · Estimated45.8Value · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.1 (estimated) · 0/19 observed / reasoning 54.2 (estimated) · 0/13 observed / writing 45.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.2-exp · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3-TTS-Flash-Realtime
qwen3-tts-flash-realtimeIndependent modelQwen · GA2025-11-27No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Z-Image-Turbo
Awaiting verification (UTC+8)
z-image-turboIndependent modelAlibaba Cloud · GA2025-11-26Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance28.8Value50.2
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentOutput usage · Image · per image27,398 points
FLUX.2 [flex]
Awaiting verification (UTC+8)
flux.2-flexIndependent modelBlack Forest Labs · GA2025-11-25Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance46.8Value32.8
Input usage · Image · per megapixel100,000 pointsOutput usage · Image · per megapixel100,000 points
FLUX.2 Pro
Awaiting verification (UTC+8)
flux.2-proIndependent modelBlack Forest Labs · GA2025-11-25Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance49.9Value64.9
Initial megapixel · per megapixel60,000 pointsAdditional megapixel · per megapixel30,000 points
claude-opus-4-5
claude-opus-4-5Independent modelAnthropic · GA2025-11-24No fixed price; billed by the underlying servicePerformance · Estimated67.9Value—
Shared exact-model performance from claude-opus-4-5; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.9 (estimated) · 0/19 observed / reasoning 71.8 (estimated) · 0/13 observed / writing 67.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-opus-4-6 · 7 benchmarksReference: claude-opus-4-5-20251101 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
claude-opus-4-5-100
claude-opus-4-5-100Independent modelAnthropic · GA2025-11-24No fixed price; billed by the underlying servicePerformance · Estimated67.9Value—
Shared exact-model performance from claude-opus-4-5; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.9 (estimated) · 0/19 observed / reasoning 71.8 (estimated) · 0/13 observed / writing 67.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-opus-4-6 · 7 benchmarksReference: claude-opus-4-5-20251101 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Grok 4.1 Fast Non-Reasoning
Awaiting verification (UTC+8)
grok-4-1-fast-non-reasoningIndependent modelxAI · GA2025-11-19Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated62.1
Shared exact-model performance from grok-4-1-fast-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens400,000 pointsCache-hit usage · per million Tokens100,000 pointsOutput usage · per million Tokens1,000,000 points
Grok 4.1 Fast Reasoning
Awaiting verification (UTC+8)
grok-4-1-fast-reasoningIndependent modelxAI · GA2025-11-19Last price verificationAwaiting verification (UTC+8)
Performance · Estimated59.5Value · Estimated64.1
Shared exact-model performance from grok-4-1-fast-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.3 (estimated) · 2/19 observed / reasoning 65.8 (estimated) · 1/13 observed / writing 59.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput usage · per million Tokens400,000 pointsCache-hit usage · per million Tokens100,000 pointsOutput usage · per million Tokens1,000,000 points
Gemini 3 Pro Preview-100
gemini-3-pro-previewIndependent modelGoogle · GA2025-11-18No fixed price; billed by the underlying servicePerformance · Estimated69.4Value · Estimated63.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 48.1 (estimated) · 0/19 observed / reasoning 77.5 (estimated) · 0/13 observed / writing 82.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.1-pro-preview-high · 7 benchmarksReference: gemini-3-pro · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Veo 3.1 Fast Generate 001-100
veo-3.1-fast-generate-001Independent modelGoogle · GA2025-11-17No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Veo 3.1 Generate 001-100
veo-3.1-generate-001Independent modelGoogle · GA2025-11-17No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT-5.1
Awaiting verification (UTC+8)
gpt-5.1Independent modelOpenAI · GA2025-11-13Last price verificationAwaiting verification (UTC+8)
Performance · Estimated63.8Value · Estimated57.2
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.9 (estimated) · 2/19 observed / reasoning 73.2 (estimated) · 1/13 observed / writing 63.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput usage · per million Tokens2,500,000 pointsCache-hit usage · per million Tokens250,000 pointsOutput usage · per million Tokens20,000,000 points
GPT-5.1 Codex
Awaiting verification (UTC+8)
gpt-5.1-codexIndependent modelOpenAI · GA2025-11-13Last price verificationAwaiting verification (UTC+8)
Performance · Estimated63.6Value · Estimated57.1
1/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.2 (estimated) · 1/19 observed / reasoning 70.3 (estimated) · 0/13 observed / writing 62.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.1 · 4 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,500,000 pointsCache-hit usage · per million Tokens250,000 pointsOutput usage · per million Tokens20,000,000 points
GPT-5.1 Codex Mini
Awaiting verification (UTC+8)
gpt-5.1-codex-miniIndependent modelOpenAI · GA2025-11-13Last price verificationAwaiting verification (UTC+8)
Performance · Estimated43.1Value · Estimated49.4
1/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.6 (estimated) · 1/19 observed / reasoning 48.9 (estimated) · 0/13 observed / writing 40.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4-mini · 7 benchmarksReference: gpt-5-mini · 4 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens500,000 pointsCache-hit usage · per million Tokens50,000 pointsOutput usage · per million Tokens4,000,000 points
Lyria 002-100
lyria-002Independent modelGoogle · GA2025-10-27No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ2_reference2video
qwen-vidu-viduq2_reference2videoIndependent modelvidu · GA2025-10-21No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ2_text2video
qwen-vidu-viduq2_text2videoIndependent modelvidu · GA2025-10-21No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Vanchin/DeepSeek-OCR
qwen-vanchin-deepseek-ocrIndependent modelDeepSeek · GA2025-10-20No fixed price; billed by the underlying servicePerformance · Estimated81.8Value · Estimated72.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · OfficialDynamic: router input markup plus the points for the model selected for each request.
claude-haiku-4-5
claude-haiku-4-5Independent modelAnthropic · GA2025-10-15No fixed price; billed by the underlying servicePerformance · Estimated60.4Value · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.5 (estimated) · 0/19 observed / reasoning 63.8 (estimated) · 0/13 observed / writing 60.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-haiku-4-5-20251001 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
claude-haiku-4-5-100
claude-haiku-4-5-100Independent modelAnthropic · GA2025-10-15No fixed price; billed by the underlying servicePerformance · Estimated60.4Value · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.5 (estimated) · 0/19 observed / reasoning 63.8 (estimated) · 0/13 observed / writing 60.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-haiku-4-5-20251001 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT-5 Pro
Awaiting verification (UTC+8)
gpt-5-proIndependent modelOpenAI · GA2025-10-06Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.5Value · Estimated41.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.9 (estimated) · 0/19 observed / reasoning 61.9 (estimated) · 0/13 observed / writing 51.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5 · 5 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens20,000,000 pointsOutput usage · per million Tokens240,000,000 points
GPT Audio Mini
Awaiting verification (UTC+8)
gpt-audio-miniIndependent modelOpenAI · GA2025-10-06Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated52.6Value · Estimated66.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · OfficialInput usage · per million Tokens1,200,000 pointsOutput usage · per million Tokens4,800,000 pointsInput usage · Audio · per million Tokens20,000,000 pointsOutput usage · Audio · per million Tokens40,000,000 points
GPT Image 1 Mini
Awaiting verification (UTC+8)
gpt-image-1-miniIndependent modelOpenAI · GA2025-10-06Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance20.1Value44.1
Input usage · per million Tokens4,000,000 pointsCache-hit usage · per million Tokens400,000 pointsInput usage · Image · per million Tokens5,000,000 pointsCache-hit usage · Image · per million Tokens500,000 pointsOutput usage · Image · per million Tokens16,000,000 points
GPT Realtime Mini
Awaiting verification (UTC+8)
gpt-realtime-miniIndependent modelOpenAI · GA2025-10-06Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated54.0Value · Estimated67.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-realtime-2025-08-28 · 59.9Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · OfficialInput usage · per million Tokens1,200,000 pointsCache-hit usage · per million Tokens120,000 pointsOutput usage · per million Tokens4,800,000 pointsInput usage · Image · per million Tokens1,600,000 pointsCache-hit usage · Image · per million Tokens160,000 pointsInput usage · Audio · per million Tokens20,000,000 pointsCache-hit usage · Audio · per million Tokens600,000 pointsOutput usage · Audio · per million Tokens40,000,000 points
Gemini 2.5 Flash TTS-100
gemini-2.5-flash-ttsIndependent modelGoogle · GA2025-09-30No fixed price; billed by the underlying servicePerformance · Estimated87.1Value · Estimated76.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Gemini-flash · 87.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Gemini 2.5 Pro TTS-100
gemini-2.5-pro-ttsIndependent modelGoogle · GA2025-09-30No fixed price; billed by the underlying servicePerformance · Estimated82.6Value · Estimated72.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Sora 2
Awaiting verification (UTC+8)
sora-2Independent modelOpenAI · Preview2025-09-30Last price verificationAwaiting verification (UTC+8)
Performance66.0Value50.4
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentVideo generation · per second200,000 points
claude-sonnet-4-5
claude-sonnet-4-5Independent modelAnthropic · GA2025-09-29No fixed price; billed by the underlying servicePerformance · Estimated61.6Value · Estimated58.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.8 (estimated) · 0/19 observed / reasoning 66.2 (estimated) · 0/13 observed / writing 59.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-sonnet-4-6 · 7 benchmarksReference: claude-sonnet-4-5-20250929 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ2-Pro_img2video
qwen-vidu-viduq2-pro_img2videoIndependent modelvidu · GA2025-09-24No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ2-Pro_start-end2video
qwen-vidu-viduq2-pro_start-end2videoIndependent modelvidu · GA2025-09-24No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ2-Turbo_img2video
qwen-vidu-viduq2-turbo_img2videoIndependent modelvidu · GA2025-09-24No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ2-Turbo_start-end2video
qwen-vidu-viduq2-turbo_start-end2videoIndependent modelvidu · GA2025-09-24No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT-5 Codex
Awaiting verification (UTC+8)
gpt-5-codexIndependent modelOpenAI · GA2025-09-23Last price verificationAwaiting verification (UTC+8)
Performance · Estimated59.1Value · Estimated53.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 59.5 (estimated) · 0/19 observed / reasoning 63.0 (estimated) · 0/13 observed / writing 54.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5 · 5 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,500,000 pointsCache-hit usage · per million Tokens250,000 pointsOutput usage · per million Tokens20,000,000 points
qwen-SiliconFlow DeepSeek-V3.1-Terminus
qwen-siliconflow-deepseek-v3.1-terminusIndependent modelDeepSeek · GA2025-09-22No fixed price; billed by the underlying servicePerformance · Estimated44.9Value · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Vanchin/DeepSeek-V3.1-Terminus
qwen-vanchin-deepseek-v3.1-terminusIndependent modelDeepSeek · GA2025-09-22No fixed price; billed by the underlying servicePerformance · Estimated44.9Value · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3-TTS-Flash
Awaiting verification (UTC+8)
qwen3-tts-flashIndependent modelAlibaba Cloud · GA2025-09 (official month only)Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated74.4Value · Estimated82.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · OfficialAudio · per 10,000 characters219,179 points
Chirp 3-100
chirp-3Independent modelGoogle · GA2025-08-29No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT Realtime
Awaiting verification (UTC+8)
gpt-realtimeIndependent modelOpenAI · GA2025-08-28Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated59.9Value · Estimated41.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · OfficialInput usage · per million Tokens8,000,000 pointsCache-hit usage · per million Tokens800,000 pointsOutput usage · per million Tokens32,000,000 pointsInput usage · Image · per million Tokens10,000,000 pointsCache-hit usage · Image · per million Tokens1,000,000 pointsInput usage · Audio · per million Tokens64,000,000 pointsCache-hit usage · Audio · per million Tokens800,000 pointsOutput usage · Audio · per million Tokens128,000,000 points
GPT-5
Awaiting verification (UTC+8)
gpt-5Independent modelOpenAI · GA2025-08-07Last price verificationAwaiting verification (UTC+8)
Performance · Estimated58.7Value · Estimated53.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.6 (estimated) · 2/19 observed / reasoning 65.6 (estimated) · 1/13 observed / writing 56.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · IndependentInput usage · per million Tokens2,500,000 pointsCache-hit usage · per million Tokens250,000 pointsOutput usage · per million Tokens20,000,000 points
GPT-5 Mini
Awaiting verification (UTC+8)
gpt-5-miniIndependent modelOpenAI · GA2025-08-07Last price verificationAwaiting verification (UTC+8)
Performance · Estimated43.1Value · Estimated49.4
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.6 (estimated) · 1/19 observed / reasoning 48.9 (estimated) · 1/13 observed / writing 40.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4-mini · 7 benchmarksReference: gpt-5.1-codex-mini · 1 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens500,000 pointsCache-hit usage · per million Tokens50,000 pointsOutput usage · per million Tokens4,000,000 points
GPT-5 Nano
Awaiting verification (UTC+8)
gpt-5-nanoIndependent modelOpenAI · GA2025-08-07Last price verificationAwaiting verification (UTC+8)
Performance · Estimated44.4Value · Estimated57.0
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 43.4 (estimated) · 1/19 observed / reasoning 50.3 (estimated) · 1/13 observed / writing 39.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-nano-2025-04-14 · 7 benchmarksReference: gpt-5.4-nano · 7 benchmarksReference: gpt-5 · 1 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens100,000 pointsCache-hit usage · per million Tokens10,000 pointsOutput usage · per million Tokens800,000 points
GPT-OSS 120B-100
openai-gpt-oss-120b-maas-001Independent modelOpenAI · GA2025-08-05No fixed price; billed by the underlying servicePerformance · Estimated57.3Value · Estimated55.1
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.4 (estimated) · 1/19 observed / reasoning 63.0 (estimated) · 1/13 observed / writing 51.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3-Coder-Flash
Awaiting verification (UTC+8)
qwen3-coder-flashIndependent modelQwen · GA2025-08-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated58.2Value · Estimated64.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 32,000 TokenInput usage · per million Tokens273,973 pointsCache-hit usage · per million Tokens54,795 pointsOutput usage · per million Tokens1,095,890 points
Input 32,001 – 128,000 TokenInput usage · per million Tokens410,959 pointsCache-hit usage · per million Tokens82,192 pointsOutput usage · per million Tokens1,643,836 points
Input 128,001 – 256,000 TokenInput usage · per million Tokens684,932 pointsCache-hit usage · per million Tokens136,986 pointsOutput usage · per million Tokens2,739,726 points
Input 256,001+ TokenInput usage · per million Tokens1,369,863 pointsCache-hit usage · per million Tokens273,973 pointsOutput usage · per million Tokens6,849,315 points
Qwen-Flash
Awaiting verification (UTC+8)
qwen-flashIndependent modelQwen · GA2025-08-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated59.4Value · Estimated70.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.4 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 128,000 TokenInput usage · per million Tokens41,096 pointsCache-hit usage · per million Tokens8,219 pointsOutput usage · per million Tokens410,959 points
Input 128,001 – 256,000 TokenInput usage · per million Tokens164,384 pointsCache-hit usage · per million Tokens32,877 pointsOutput usage · per million Tokens1,643,836 points
Input 256,001+ TokenInput usage · per million Tokens328,767 pointsCache-hit usage · per million Tokens65,753 pointsOutput usage · per million Tokens3,287,671 points
doubao-glm-4-5-air
doubao-glm-4-5-air-20250728Fixed snapshot / version · Sole entryZhipu AI · GA2025-07-28No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
GLM-4.5-Air
Awaiting verification (UTC+8)
glm-4.5-airIndependent modelZhipu · GA2025-07-27Last price verificationAwaiting verification (UTC+8)
Performance · Estimated59.3Value · Estimated64.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.9 (estimated) · 0/19 observed / reasoning 64.2 (estimated) · 0/13 observed / writing 55.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-4.5-air · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 31,999 Token · Output 0 – 199 TokenInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens43,836 pointsOutput usage · per million Tokens547,945 points
Input 0 – 31,999 Token · Output 200+ TokenInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens43,836 pointsOutput usage · per million Tokens1,643,836 points
Input 32,000+ TokenInput usage · per million Tokens328,767 pointsCache-hit usage · per million Tokens65,753 pointsOutput usage · per million Tokens2,191,781 points
qwen-pixverse/pixverse-lipsync
qwen-pixverse-pixverse-lipsyncIndependent modelpixverse · GA2025-07-14No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Plus
Awaiting verification (UTC+8)
qwen-plusIndependent modelQwen · GA2025-06-24Last price verificationAwaiting verification (UTC+8)
Performance · Estimated44.2Value · Estimated55.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.6 (estimated) · 0/19 observed / reasoning 46.7 (estimated) · 0/13 observed / writing 40.3 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput 0 – 128,000 TokenInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens43,836 pointsOutput usage · per million Tokens547,945 points
Input 128,001 – 256,000 TokenInput usage · per million Tokens657,534 pointsCache-hit usage · per million Tokens131,507 pointsOutput usage · per million Tokens5,479,452 points
Input 256,001+ TokenInput usage · per million Tokens1,315,068 pointsCache-hit usage · per million Tokens263,014 pointsOutput usage · per million Tokens13,150,685 points
qwen-SiliconFlow DeepSeek-R1-0528
qwen-siliconflow-deepseek-r1-0528Independent modelDeepSeek · GA2025-05-28No fixed price; billed by the underlying servicePerformance · Estimated43.2Value · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Mistral OCR 2505-100
mistralai-mistral-ocr-2505-001Independent modelMistral AI · GA2025-05-22No fixed price; billed by the underlying servicePerformance · Estimated81.8Value · Estimated72.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · OfficialDynamic: router input markup plus the points for the model selected for each request.
mistral-medium-2505
mistral-medium-2505Independent modelMistral AI · GA2025-05-07No fixed price; billed by the underlying servicePerformance · Estimated54.1Value · Estimated52.9
Version comparison review4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.4 (estimated) · 1/19 observed / reasoning 59.7 (estimated) · 1/13 observed / writing 55.3 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below mistral-medium-3-5 by 6.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Phi-4 Reasoning
Awaiting verification (UTC+8)
phi-4-reasoningIndependent modelMicrosoft · GA2025-04-30Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens250,000 pointsOutput usage · per million Tokens1,000,000 points
o3
Awaiting verification (UTC+8)
o3Independent modelOpenAI · GA2025-04-16Last price verificationAwaiting verification (UTC+8)
Performance · Estimated62.8Value · Estimated56.1
7/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 18%coding 57.9 (estimated) · 1/19 observed / reasoning 70.4 (estimated) · 4/13 observed / writing 60.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: o3-2025-04-16 · 4 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksReference: DeepSeek V4 Pro (High) (0813) · 1 benchmarksopenai-simple-evals · Officialmicrosoft-mai-report · Officialmistral-codestral · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens4,000,000 pointsCache-hit usage · per million Tokens1,000,000 pointsOutput usage · per million Tokens16,000,000 points
Veo 2.0 Generate 001-100
veo-2.0-generate-001Independent modelGoogle · GA2025-04-09No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Llama 4 Maverick 17B 128E
Awaiting verification (UTC+8)
llama-4-maverick-17b-128e-instruct-fp8Independent modelMeta · GA2025-04-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated60.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens500,000 pointsOutput usage · per million Tokens2,000,000 points
Llama 4 Maverick 17B 128E-100
llama-4-maverick-17b-128e-instruct-maas-100Independent modelMeta · GA2025-04-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Llama 4 Scout 17B 16E Instruct-100
meta-llama-4-scout-17b-16e-instruct-maas-001Independent modelMeta · GA2025-04-05No fixed price; billed by the underlying servicePerformance · Estimated53.1Value · Estimated52.2
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.1 (estimated) · 1/19 observed / reasoning 56.7 (estimated) · 1/13 observed / writing 47.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-SiliconFlow DeepSeek-V3-0324
qwen-siliconflow-deepseek-v3-0324Independent modelDeepSeek · GA2025-03-24No fixed price; billed by the underlying servicePerformance · Estimated39.9Value · Estimated42.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.0 (estimated) · 0/19 observed / reasoning 48.3 (estimated) · 0/13 observed / writing 35.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-coder-480b-a35b-instruct · 5 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below qwen-deepseek-r1-0528 by 4.6 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
GPT-4o Mini Transcribe
Awaiting verification (UTC+8)
gpt-4o-mini-transcribeIndependent modelOpenAI · GA2025-03-20Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated91.4Value · Estimated94.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentInput usage · Audio · per million Tokens6,000,000 pointsInput usage · per million Tokens2,500,000 pointsOutput usage · per million Tokens10,000,000 points
GPT-4o Mini TTS
Awaiting verification (UTC+8)
gpt-4o-mini-ttsIndependent modelOpenAI · GA2025-03-20Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated59.8Value · Estimated56.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: GPT-4o-mini-tts · 59.8qwen-tts-public · OfficialInput usage · per million Tokens1,200,000 pointsOutput usage · Audio · per million Tokens24,000,000 points
GPT-4o Transcribe
Awaiting verification (UTC+8)
gpt-4o-transcribeIndependent modelOpenAI · GA2025-03-20Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance91.4Value64.0
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 18%qwen-asr-report · IndependentInput usage · Audio · per million Tokens12,000,000 pointsInput usage · per million Tokens5,000,000 pointsOutput usage · per million Tokens20,000,000 points
mistral-small-2503
mistral-small-2503Independent modelMistral AI · GA2025-03-17No fixed price; billed by the underlying servicePerformance · Estimated56.0Value—
Shared exact-model performance from mistral-small-2503; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.7 (estimated) · 0/19 observed / reasoning 59.2 (estimated) · 0/13 observed / writing 52.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: mistral-small-2506 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Mistral Small 3.1-100
Awaiting verification (UTC+8)
mistral-small-2503-100Independent modelGoogle · Preview2025-03-17Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.0Value · Estimated64.3
Shared exact-model performance from mistral-small-2503; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.7 (estimated) · 0/19 observed / reasoning 59.2 (estimated) · 0/13 observed / writing 52.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: mistral-small-2506 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens200,000 pointsOutput usage · per million Tokens600,000 points
Text Embedding Large Exp 03 07-100
text-embedding-large-exp-03-07Independent modelGoogle · GA2025-03-07No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-DeepSeek-R1-Distill-Qwen-1.5B
qwen-deepseek-r1-distill-qwen-1.5bIndependent modelDeepSeek · GA2025-01-20No fixed price; billed by the underlying servicePerformance · Estimated43.2Value · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Codestral 2501
Awaiting verification (UTC+8)
codestral-2501Independent modelMistral AI · GA2025-01-13Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated60.1
9/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 18%coding 56.8 (estimated) · 9/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksReference: smaug-flash · 3 benchmarksmistral-codestral · Officialmicrosoft-mai-report · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens600,000 pointsOutput usage · per million Tokens1,800,000 points
Ministral-3B
ministral-3bIndependent modelMistral AI · GA2024-10-16No fixed price; billed by the underlying servicePerformance · Estimated49.2Value · Estimated49.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.8 (estimated) · 0/19 observed / reasoning 50.7 (estimated) · 0/13 observed / writing 43.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: ministral-8b-2410 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Long
Awaiting verification (UTC+8)
qwen-longIndependent modelQwen · GA2024-05-20Last price verificationAwaiting verification (UTC+8)
Performance · Estimated52.5Value · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 48.7 (estimated) · 0/19 observed / reasoning 58.7 (estimated) · 0/13 observed / writing 50.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: qwen-glm-4.5 · 4 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens136,986 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens547,945 points
Text Embedding 3 Large
Awaiting verification (UTC+8)
text-embedding-3-largeIndependent modelOpenAI · GA2024-01-25Last price verificationAwaiting verification (UTC+8)
Performance64.6Value45.2
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · OfficialEmbedding input · per million Tokens260,000 points
Text Embedding 3 Small
Awaiting verification (UTC+8)
text-embedding-3-smallIndependent modelOpenAI · GA2024-01-25Last price verificationAwaiting verification (UTC+8)
Performance62.3Value71.3
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · OfficialEmbedding input · per million Tokens40,000 points
Cohere-embed-v3-english
cohere-embed-v3-englishIndependent modelCohere · GA2023-11-02No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Cohere-embed-v3-multilingual
cohere-embed-v3-multilingualIndependent modelCohere · GA2023-11-02No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Text Embedding Ada 002
Awaiting verification (UTC+8)
text-embedding-ada-002Independent modelOpenAI · GA2022-12-15Last price verificationAwaiting verification (UTC+8)
Performance61.0Value46.6
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · OfficialEmbedding input · per million Tokens200,000 points
Qwen-Image-2.1-Turbo
qwen-image-2.1-turboIndependent modelQwen · GACatalogue added (release date pending): 2026-10-14No fixed price; billed by the underlying servicePerformance—Value—
Not ratedDynamic: router input markup plus the points for the model selected for each request.
Chirp 2-100
chirp-2-001Independent modelGoogle · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
语音生成CosyVoice-v3.5-flash大模型
cosyvoice-v3.5-flashIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated75.4Value · Estimated67.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
语音生成CosyVoice-v3.5-plus大模型
cosyvoice-v3.5-plusIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated75.4Value · Estimated67.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
doubao-GLM-5.3-Flash
Awaiting verification (UTC+8)
doubao-glm-5-3-flash-260828Fixed snapshot / version · Sole entryZhipu · GACatalogue added (release date pending): 2026-10-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 56.6microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens63,014 pointsOutput usage · per million Tokens767,123 points
qwen2-5-72b
doubao-qwen2-5-72b-20240919Fixed snapshot / version · Sole entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen3-0-6b
doubao-qwen3-0-6b-20250429Fixed snapshot / version · Sole entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen3-14b
doubao-qwen3-14b-20250429Fixed snapshot / version · Sole entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen3-32b
doubao-qwen3-32b-20250429Fixed snapshot / version · Sole entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen3-8b
doubao-qwen3-8b-20250429Fixed snapshot / version · Sole entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
doubao-seed-translation
doubao-seed-translation-250915Fixed snapshot / version · Sole entryDoubao · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
doubao-smart-router
doubao-smart-router-250928Fixed snapshot / version · Sole entryDoubao · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated50.0Value · Estimated50.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: o1-mini · 50.0Reference: qwen3.6-plus · 50.2Reference: gemini-2.0-flash-001 · 50.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
FaceChain人物图像检测
facechain-facedetectIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated44.5Value · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Fun-ASR语音识别
fun-asrIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
Fun-ASR实时语音识别
fun-asr-realtimeIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
音乐生成 Preview
fun-music-previewIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
音乐生成
fun-music-v1Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Grok 4.20 Non-Reasoning-100
Awaiting verification (UTC+8)
grok-4-20-non-reasoning-100Independent modelxAI · GACatalogue added (release date pending): 2026-10-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value—
Shared exact-model performance from grok-4-20-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens2,500,000 pointsCache-hit usage · per million Tokens400,000 pointsOutput usage · per million Tokens5,000,000 points
Grok 4.20 Reasoning-100
grok-4-20-reasoning-100Independent modelxAI · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value—
Shared exact-model performance from grok-4-20-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Grok 4.3-100
grok-4.3-100Independent modelxAI · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated44.8Value—
Shared exact-model performance from grok-4.3; coverage refers to public model benchmarks, not tests of every platform deployment.12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.8 (estimated) · 4/19 observed / reasoning 48.3 (estimated) · 4/13 observed / writing 47.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-HappyHorse-1.0-Video-Edit
happyhorse-1.0-video-editIndependent modelHappyHorse · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated80.9Value · Estimated71.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
图像擦除补全
image-erase-completionIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated44.5Value · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
人物实例分割
image-instance-segmentationIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated44.5Value · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Codestral 2-100
mistralai-codestral-2-001Independent modelMistral AI · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Mistral Medium 3-100
mistralai-mistral-medium-3-001Independent modelMistral AI · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Paraformer语音识别-8k-v2
paraformer-8k-v2Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Paraformer实时语音识别-8k-v2
paraformer-realtime-8k-v2Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Paraformer实时语音识别-v2
paraformer-realtime-v2Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Paraformer语音识别-v2
paraformer-v2Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3-ASR-Flash-Filetrans
qwen3-asr-flash-filetransIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen3-ASR-Flash-Realtime
qwen3-asr-flash-realtimeIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated52.6Value · Estimated51.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Qwen-Audio-3.1-ASR-Flash
qwen-audio-3.1-asr-flashIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Audio-3.1-ASR-Flash-Filetrans
qwen-audio-3.1-asr-flash-filetransIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Audio-3.1-ASR-Flash-Message
qwen-audio-3.1-asr-flash-messageIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Audio-3.1-ASR-Flash-Streaming
qwen-audio-3.1-asr-flash-streamingIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated91.4Value · Estimated79.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Audio-3.1-TTS-Flash
qwen-audio-3.1-tts-flashIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated74.4Value · Estimated67.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Qwen-Audio-3.1-TTS-Next
qwen-audio-3.1-tts-nextIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated74.4Value · Estimated67.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · OfficialDynamic: router input markup plus the points for the model selected for each request.
Qwen-Doc-Turbo
Awaiting verification (UTC+8)
qwen-doc-turboIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated48.7Value · Estimated49.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.8 (estimated) · 0/19 observed / reasoning 52.3 (estimated) · 0/13 observed / writing 47.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens164,384 pointsCache-hit usage · per million Tokens32,877 pointsOutput usage · per million Tokens273,973 points
Qwen-Flash-Character
Awaiting verification (UTC+8)
qwen-flash-characterIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated59.9Value · Estimated70.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.1 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens68,493 pointsCache-hit usage · per million Tokens13,699 pointsOutput usage · per million Tokens410,959 points
qwen-Kling Video 3.0 Turbo
qwen-kling-kling-v3-turbo-video-generationIndependent modelkling · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-speech-02-hd
qwen-minimax-speech-02-hdIndependent modelmini-max · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated32.9Value · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 32.7 (estimated) · 0/19 observed / reasoning 39.5 (estimated) · 0/13 observed / writing 26.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-speech-02-turbo
qwen-minimax-speech-02-turboIndependent modelmini-max · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated34.1Value · Estimated38.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 39.8 (estimated) · 0/13 observed / writing 28.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-speech-2.8-hd
qwen-minimax-speech-2.8-hdIndependent modelmini-max · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated44.1Value · Estimated45.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.0 (estimated) · 0/19 observed / reasoning 53.2 (estimated) · 0/13 observed / writing 41.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-instruct-2507 · 4 benchmarksReference: qwen3-235b-a22b-thinking-2507 · 4 benchmarksReference: qwen3-30b-a3b-instruct-2507 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-speech-2.8-turbo
qwen-minimax-speech-2.8-turboIndependent modelmini-max · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated46.9Value · Estimated47.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 40.0 (estimated) · 0/19 observed / reasoning 56.2 (estimated) · 0/13 observed / writing 44.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen3-30b-a3b-instruct-2507 · 4 benchmarksReference: qwen3-max-2025-09-23 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-MT-Flash
qwen-mt-flashIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated59.4Value · Estimated56.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-MT-Image
qwen-mt-imageIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated34.1Value · Estimated38.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image · 20.0Reference: qwen-image-prompt-extend · 23.8Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-MT-Lite
qwen-mt-liteIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.3Value · Estimated54.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 0/19 observed / reasoning 60.6 (estimated) · 0/13 observed / writing 58.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: qwen3.8-max · 8 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-MT-Plus
qwen-mt-plusIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated46.7Value · Estimated47.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.9 (estimated) · 0/19 observed / reasoning 50.1 (estimated) · 0/13 observed / writing 43.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-PixVerse-V6-r2v
qwen-pixverse-pixverse-v6-r2vIndependent modelpixverse · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Plus-Character
Awaiting verification (UTC+8)
qwen-plus-characterIndependent modelqwen-domain-model · GACatalogue added (release date pending): 2026-10-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated46.9Value · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.0 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 43.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens219,178 pointsCache-hit usage · per million Tokens43,836 pointsOutput usage · per million Tokens547,945 points
qwen-stepfun/step-5-preview
Awaiting verification (UTC+8)
qwen-stepfun-step-5-previewIndependent modelStepFun · GACatalogue added (release date pending): 2026-10-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated30.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens1,917,808 pointsCache-hit usage · per million Tokens95,890 pointsOutput usage · per million Tokens5,479,452 points
qwen-unisound/unisound-u2
qwen-unisound-unisound-u2Independent modelunisound · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated32.9Value · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 32.7 (estimated) · 0/19 observed / reasoning 39.5 (estimated) · 0/13 observed / writing 26.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Vanchin/DeepSeek-R1
qwen-vanchin-deepseek-r1Independent modelDeepSeek · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated43.2Value · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Vanchin/DeepSeek-V3
qwen-vanchin-deepseek-v3Independent modelDeepSeek · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated42.6Value · Estimated44.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.2 (estimated) · 0/19 observed / reasoning 51.7 (estimated) · 0/13 observed / writing 39.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-no-thinking · 4 benchmarksReference: qwen3-next-80b-a3b-thinking · 4 benchmarksReference: qwen3-vl-235b-a22b-thinking · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below qwen-deepseek-r1-0528 by 1.9 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-vanchin/deepseek-v4-pro
qwen-vanchin-deepseek-v4-proIndependent modelDeepSeek · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated71.1Value · Estimated64.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 67.0 (estimated) · 0/19 observed / reasoning 75.3 (estimated) · 0/13 observed / writing 70.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-max · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: qwen3.8-27b · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Vidu-image-lite_reference2image
qwen-vidu-vidu-image-lite_reference2imageIndependent modelvidu · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated66.4Value · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Vidu-image-pro_reference2image
qwen-vidu-vidu-image-pro_reference2imageIndependent modelvidu · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated66.4Value · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Vidu-image_reference2image
qwen-vidu-vidu-image_reference2imageIndependent modelvidu · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated73.8Value · Estimated66.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ2-fast_reference2image
qwen-vidu-viduq2-fast_reference2imageIndependent modelvidu · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated66.4Value · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ2-Pro_reference2image
qwen-vidu-viduq2-pro_reference2imageIndependent modelvidu · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated66.4Value · Estimated61.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-Ad_reference2video
qwen-vidu-viduq3-ad_reference2videoIndependent modelvidu · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-Drama_reference2video
qwen-vidu-viduq3-drama_reference2videoIndependent modelvidu · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-fast_reference2image
qwen-vidu-viduq3-fast_reference2imageIndependent modelvidu · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated85.0Value · Estimated74.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-3.0-pro · 85.0Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ViduQ3-Pro-fast_img2video
qwen-vidu-viduq3-pro-fast_img2videoIndependent modelvidu · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Qwen-Voice-Enrollment
qwen-voice-enrollmentIndependent service entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.7 (estimated) · 0/19 observed / reasoning 56.4 (estimated) · 0/13 observed / writing 50.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-ZHIPU/GLM-5.3-FlashX
Awaiting verification (UTC+8)
qwen-zhipu-glm-5.3-flashxIndependent modelZhipu AI · GACatalogue added (release date pending): 2026-10-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated41.0Value · Estimated37.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens547,945 pointsCache-hit usage · per million Tokens156,164 pointsOutput usage · per million Tokens1,917,808 points
Sambert语音合成-Beth
sambert-beth-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Betty
sambert-betty-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Brian
sambert-brian-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Cally
sambert-cally-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Camila
sambert-camila-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Cindy
sambert-cindy-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Clara
sambert-clara-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Donna
sambert-donna-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Eva
sambert-eva-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Hanna
sambert-hanna-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Indah
sambert-indah-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Perla
sambert-perla-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-Waan
sambert-waan-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知厨
sambert-zhichu-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知达
sambert-zhida-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知德
sambert-zhide-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知飞
sambert-zhifei-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知柜
sambert-zhigui-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated44.5Value · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知浩
sambert-zhihao-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知佳
sambert-zhijia-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知婧
sambert-zhijing-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知伦
sambert-zhilun-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知猫
sambert-zhimao-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知妙（多情感）
sambert-zhimiao-emo-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知茗
sambert-zhiming-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知墨
sambert-zhimo-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知楠
sambert-zhinan-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知娜
sambert-zhina-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知倩
sambert-zhiqian-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知琪
sambert-zhiqi-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知茹
sambert-zhiru-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知硕
sambert-zhishuo-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知树
sambert-zhishu-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知莎
sambert-zhistella-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知婷
sambert-zhiting-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知薇
sambert-zhiwei-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知祥
sambert-zhixiang-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知笑
sambert-zhixiao-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知雅
sambert-zhiya-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知晔
sambert-zhiye-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知颖
sambert-zhiying-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知媛
sambert-zhiyuan-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Sambert语音合成-知悦
sambert-zhiyue-v1Independent voice entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
鞋靴模特
shoemodel-v1Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated44.5Value · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
语音识别热词
speech-biasingIndependent service entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
通用文本向量-async-v1
text-embedding-async-v1Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
通用文本向量-async-v2
text-embedding-async-v2Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
意图分类模型
tongyi-intent-detect-v3Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
伶鹊-对话分析-flash
Awaiting verification (UTC+8)
tongyi-xiaomi-analysis-flashIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens54,795 pointsCache-hit usage · per million Tokens10,959 pointsOutput usage · per million Tokens109,589 points
伶鹊-对话分析-pro
Awaiting verification (UTC+8)
tongyi-xiaomi-analysis-proIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens273,973 pointsCache-hit usage · per million Tokens54,795 pointsOutput usage · per million Tokens739,726 points
Translate LLM-100
translate-llmIndependent modelGoogle · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
声动人像VideoRetalk
videoretalkIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
视频风格重绘
video-style-transformIndependent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated51.0Value · Estimated50.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
虚拟模特V2
virtualmodel-v2Independent modelQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated44.5Value · Estimated46.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
大模型声音复刻及声音设计
voice-enrollmentIndependent service entryQwen · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated56.6Value · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.2-Animate-Mix
wan2.2-animate-mixIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.2-Animate-Move
wan2.2-animate-moveIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.2-KF2V-Flash
wan2.2-kf2v-flashIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-通义万相2.2-数字人-S2V
wan2.2-s2vIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.2-S2V-Detect
wan2.2-s2v-detectIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.2-T2I-Flash
wan2.2-t2i-flashIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.2-T2I-Plus
wan2.2-t2i-plusIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.5-I2I-Preview
wan2.5-i2i-previewIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated52.7Value · Estimated51.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.5-T2I-Preview
wan2.5-t2i-previewIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated51.5Value · Estimated51.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: wan2.5-i2v-preview · 55.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.6-R2V-Flash
wan2.6-r2v-flashIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated55.3Value · Estimated53.7
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.0-T2I-Turbo
wanx2.0-t2i-turboIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.1-ImageEdit
wanx2.1-imageeditIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.1-KF2V-Plus
wanx2.1-kf2v-plusIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.1-T2I-Plus
wanx2.1-t2i-plusIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.1-T2I-Turbo
wanx2.1-t2i-turboIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-Wan2.1-VACE-Plus
wanx2.1-vace-plusIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-创意海报生成
wanx-poster-generation-v1Independent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-万相-涂鸦作画
wanx-sketch-to-image-liteIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated34.8Value · Estimated39.4
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-人像风格重绘
wanx-style-repaint-v1Independent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-wanx-t2i
wanx-v1Independent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-虚拟模特
wanx-virtualmodelIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated36.9Value · Estimated40.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
qwen-万相-图像局部重绘
wanx-x-paintingIndependent modelWan · GACatalogue added (release date pending): 2026-10-05No fixed price; billed by the underlying servicePerformance · Estimated37.0Value · Estimated40.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · IndependentDynamic: router input markup plus the points for the model selected for each request.
语音生成cosyvoice-v2大模型
Awaiting verification (UTC+8)
cosyvoice-v2Independent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated75.4Value · Estimated52.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · OfficialAudio · per 10,000 characters547,946 points
语音生成CosyVoice-v3-flash大模型
Awaiting verification (UTC+8)
cosyvoice-v3-flashIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated75.4Value · Estimated75.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · OfficialAudio · per 10,000 characters273,973 points
语音生成CosyVoice-v3-plus大模型
Awaiting verification (UTC+8)
cosyvoice-v3-plusIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated75.4Value · Estimated52.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · OfficialAudio · per 10,000 characters547,946 points
GUI-Plus
Awaiting verification (UTC+8)
gui-plusIndependent modelQwen · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated56.6Value · Estimated61.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · IndependentInput usage · per million Tokens410,959 pointsCache-hit usage · per million Tokens0 pointsOutput usage · per million Tokens1,232,877 points
通用多模态向量
Awaiting verification (UTC+8)
multimodal-embedding-v1Independent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated62.3Value · Estimated48.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEmbedding input · per million Tokens191,781 pointsInput usage · Image · per million Tokens246,576 pointsVideo input · per million Tokens246,576 points
Qwen2.5-VL-Embedding
Awaiting verification (UTC+8)
qwen2.5-vl-embeddingIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated62.3Value · Estimated48.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEmbedding input · per million Tokens191,781 pointsInput usage · Image · per million Tokens493,151 points
Qwen3-ASR-Flash
Awaiting verification (UTC+8)
qwen3-asr-flashIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated91.4Value · Estimated94.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentTranscription · per second61 points
千问3-Rerank
Awaiting verification (UTC+8)
qwen3-rerankIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated72.5Value · Estimated80.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · OfficialInput usage · per million Tokens136,987 points
Qwen3-VL-Embedding
Awaiting verification (UTC+8)
qwen3-vl-embeddingIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated62.3Value · Estimated48.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEmbedding input · per million Tokens191,781 pointsInput usage · Image · per million Tokens493,151 points
Qwen3-VL-Rerank
Awaiting verification (UTC+8)
qwen3-vl-rerankIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated72.5Value · Estimated80.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · OfficialInput usage · per million Tokens136,987 pointsVideo input · per million Tokens493,154 points
Customer-approved estimated video-input liability rate. The provider has not published an official video price or frame-to-Token conversion. Shown only for the catalog and acceptance reservation; it is not recorded as supplier cost and does not change historical bills.
Qwen-Image-2.0-Pro
Awaiting verification (UTC+8)
qwen-image-2.0-proIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance · Estimated66.4Value · Estimated46.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4arena · Independentarena · IndependentOutput usage · Image · per image136,987 points
Qwen-Image-3.0-Pro
Awaiting verification (UTC+8)
qwen-image-3.0-proIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance85.0Value59.5
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentImage Input usage 1K · per image5,480 pointsImage Input usage 2K · per image5,480 pointsImage Output usage 1K · per image68,494 pointsImage Output usage 2K · per image136,987 points
QwenVL-OCR
Awaiting verification (UTC+8)
qwen-vl-ocrIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated81.8Value · Estimated72.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · OfficialInput usage · per million Tokens82,192 pointsOutput usage · per million Tokens136,987 points
通用文本向量-v1
Awaiting verification (UTC+8)
text-embedding-v1Independent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance58.3Value45.3
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEmbedding input · per million Tokens191,781 points
通用文本向量-v2
Awaiting verification (UTC+8)
text-embedding-v2Independent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance60.1Value46.6
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEmbedding input · per million Tokens191,781 points
通用文本向量-v3
Awaiting verification (UTC+8)
text-embedding-v3Independent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance63.4Value53.9
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEmbedding input · per million Tokens136,987 points
通用文本向量-v4
Awaiting verification (UTC+8)
text-embedding-v4Independent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance71.6Value59.6
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEmbedding input · per million Tokens136,987 points
视觉向量-flash
Awaiting verification (UTC+8)
tongyi-embedding-vision-flashIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated62.3Value · Estimated70.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEmbedding input · per million Tokens41,096 points
视觉向量-plus
Awaiting verification (UTC+8)
tongyi-embedding-vision-plusIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated62.3Value · Estimated53.1
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · OfficialEmbedding input · per million Tokens136,987 points
Wan2.2-I2V-Flash
Awaiting verification (UTC+8)
wan2.2-i2v-flashIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated11.7Value · Estimated38.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentVideo generation 480P · per second27,398 pointsVideo generation 720P · per second54,795 pointsVideo generation 1080P · per second131,507 points
Wan2.2-I2V-Plus
Awaiting verification (UTC+8)
wan2.2-i2v-plusIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentVideo generation 480P · per second38,357 pointsVideo generation 1080P · per second191,781 points
Wan2.2-T2V-Plus
Awaiting verification (UTC+8)
wan2.2-t2v-plusIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated11.7Value · Estimated23.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentVideo generation 480P · per second38,357 pointsVideo generation 1080P · per second191,781 points
Wan2.5-I2V-Preview
Awaiting verification (UTC+8)
wan2.5-i2v-previewIndependent modelAlibaba Cloud · PreviewCatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance55.3Value46.8
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentVideo generation 480P · per second82,192 pointsVideo generation 720P · per second164,384 pointsVideo generation 1080P · per second273,973 points
Wan2.5-T2V-Preview
Awaiting verification (UTC+8)
wan2.5-t2v-previewIndependent modelAlibaba Cloud · PreviewCatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance48.9Value42.3
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentVideo generation 480P · per second82,192 pointsVideo generation 720P · per second164,384 pointsVideo generation 1080P · per second273,973 points
wan2.6-I2V-flash
Awaiting verification (UTC+8)
wan2.6-i2v-flashIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated54.9Value · Estimated60.3
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4arena · Independentarena · IndependentVideo generation 720P · per second82,192 pointsVideo generation 1080P · per second136,987 points
Wan2.1-I2V-Plus
Awaiting verification (UTC+8)
wanx2.1-i2v-plusIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated11.7Value · Estimated13.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentVideo generation 720P · per second191,781 points
Wan2.1-I2V-Turbo
Awaiting verification (UTC+8)
wanx2.1-i2v-turboIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated11.7Value · Estimated34.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentVideo generation 480P · per second65,754 pointsVideo generation 720P · per second65,754 points
Wan2.1-T2V-Plus
Awaiting verification (UTC+8)
wanx2.1-t2v-plusIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated11.7Value · Estimated13.2
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentVideo generation 720P · per second191,781 points
Wan2.1-T2V-Turbo
Awaiting verification (UTC+8)
wanx2.1-t2v-turboIndependent modelAlibaba Cloud · GACatalogue added (release date pending): 2026-09-10Last price verificationAwaiting verification (UTC+8)
Performance · Estimated11.7Value · Estimated34.6
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · IndependentVideo generation 480P · per second65,754 pointsVideo generation 720P · per second65,754 points
doubao-hitem3d-2-0-251223
Awaiting verification (UTC+8)
doubao-hitem3d-2-0-251223Fixed snapshot / version · Sole entryHitem3D · GACatalogue added (release date pending): 2026-09-09Last price verificationAwaiting verification (UTC+8)
Performance · Estimated82.2Value · Estimated57.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: doubao-seed3d-2-0-260328 · 82.2seed3d-public · OfficialOutput usage · 3D · per million Tokens21,917,809 points
doubao-hyper3d-gen2-260112
Awaiting verification (UTC+8)
doubao-hyper3d-gen2-260112Fixed snapshot / version · Sole entryHyper3D · GACatalogue added (release date pending): 2026-09-09Last price verificationAwaiting verification (UTC+8)
Performance · Estimated82.2Value · Estimated87.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: doubao-seed3d-2-0-260328 · 82.2seed3d-public · OfficialOutput usage · 3D · per million Tokens16,438,357 points
doubao-seedance-2-0-260128
Awaiting verification (UTC+8)
doubao-seedance-2-0-260128Fixed snapshot / version · Sole entryByteDance · GACatalogue added (release date pending): 2026-09-09Last price verificationAwaiting verification (UTC+8)
Performance · Estimated91.5Value · Estimated68.5
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.0-720p · 91.5arena · Independentarena · IndependentOutput usage · Video generation · per million Tokens12,602,740 points
doubao-seedance-2-0-fast-260128
Awaiting verification (UTC+8)
doubao-seedance-2-0-fast-260128Fixed snapshot / version · Sole entryByteDance · GACatalogue added (release date pending): 2026-09-09Last price verificationAwaiting verification (UTC+8)
Performance · Estimated91.5Value · Estimated70.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.0-720p · 91.5arena · Independentarena · IndependentOutput usage · Video generation · per million Tokens7,602,740 points
doubao-seedance-2-0-mini-260615
Awaiting verification (UTC+8)
doubao-seedance-2-0-mini-260615Fixed snapshot / version · Sole entryByteDance · GACatalogue added (release date pending): 2026-09-09Last price verificationAwaiting verification (UTC+8)
Performance · Estimated91.5Value · Estimated75.9
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.0-720p · 91.5arena · Independentarena · IndependentOutput usage · Video generation · per million Tokens2,520,548 points
doubao-seedream-5-0-260128
Awaiting verification (UTC+8)
doubao-seedream-5-0-260128Fixed snapshot / version · Sole entryByteDance · GACatalogue added (release date pending): 2026-09-09Available · generation and editingLast price verificationAwaiting verification (UTC+8)
Performance · Estimated54.4Value · Estimated53.4
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-4.5 · 54.4arena · Independentarena · IndependentOutput usage · Image · per image60,274 points
GPT-4o Transcribe Diarize
Awaiting verification (UTC+8)
gpt-4o-transcribe-diarizeIndependent modelOpenAI · GACatalogue added (release date pending): 2026-08-28Available · audio toolsLast price verificationAwaiting verification (UTC+8)
Performance · Estimated91.4Value · Estimated64.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · IndependentInput usage · Audio · per million Tokens12,000,000 pointsInput usage · per million Tokens5,000,000 pointsOutput usage · per million Tokens20,000,000 points
GPT Audio
Awaiting verification (UTC+8)
gpt-audioIndependent modelOpenAI · GACatalogue added (release date pending): 2026-08-28Full capabilitiesLast price verificationAwaiting verification (UTC+8)
Performance · Estimated52.6Value · Estimated36.8
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · OfficialInput usage · per million Tokens5,000,000 pointsOutput usage · per million Tokens20,000,000 pointsInput usage · Audio · per million Tokens80,000,000 pointsOutput usage · Audio · per million Tokens160,000,000 points
Mistral Document AI 2512
Awaiting verification (UTC+8)
mistral-document-ai-2512Independent modelMistral AI · GACatalogue added (release date pending): 2026-08-28Last price verificationAwaiting verification (UTC+8)
Performance96.1Value76.1
Provisional
2026-10-08 16:22 (UTC+8) · Confidence 18%mistral-ocr · OfficialDocument processing · per 1,000 pages6,000,000 points
Model Router
model-routerIndependent routing serviceOpenAI · GACatalogue added (release date pending): 2026-08-28No fixed price; billed by the underlying servicePerformance · Estimated50.0Value · Estimated50.0
Estimate basis
2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: o1-mini · 50.0Reference: qwen3.6-plus · 50.2Reference: gemini-2.0-flash-001 · 50.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-simple-evals · Officialarena · Independentarena · Independentlivebench · IndependentDynamic: router input markup plus the points for the model selected for each request.
Verified capability descriptions · 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.
CURRENT BOUNDARY
Current delivery boundary
Adds 32 non-Google models: 27 text models, Mistral Document AI, three embedding models and Sora 2. Update to Connector 1.0.86.0 and enable each plugin and its API key permission. Text API: 34 models; Codex menu: 32 models with tools. Phi and Llama support API questions only. Documents: 30 MB and 30 pages. Knowledge: selected local text files, citations and reusable local indexes. Video: 4/8/12 seconds, 720p, matching reference images and completed-video remix. Download videos promptly. Completed usage is billed; cached reads are free. Google and model-router remain excluded. Equipment identities, protocols, operating data, agents and control remain in customer-authorized local, edge or private environments. The public website introduces the service; it is not a cloud equipment-control platform.