AIEvals

Compare

Models

Specifications, pricing and published results for the models in this catalogue.

46 of 46 modelsPrices in USD / million tokens
Model specifications and source-specific scores. Open a model for its sources and configuration.
ModelReleasedContextInput / output priceWeightsT-Bench 4.0% · AAAA Index
DeepSeek V4.1 Flash 1017DeepSeek17 October 20261M tokens$0.30 / $1.20Open——
GLM-LegalZ.ai12 October 2026Not publishedNot publishedPrivate——
Claude Haiku 5.5Anthropic7 October 20261M tokensFrom $0.10 / $0.50Up to 100,000 tokens; higher rates above this limitPrivate32.8343
BeamReflection AI5 October 20261M tokens (trained)Not publishedPending——
Gemini 4 ArgonGoogle30 September 20261M tokens$2.00 / $10.00Private57.0753
GPT-6.1 SolOpenAI29 September 20261.05M tokens$2.00 / $10.00Private56.0652
Claude Sonnet 5.5Anthropic28 September 20261M tokens$2.00 / $10.00Private63.6456
GPT-6 LunaOpenAI22 September 20261M tokens$0.10 / $0.50Private12.6337
Claude Opus 5.5Anthropic22 September 20261M tokens$4.00 / $20.00Private59.6058
GPT-6 SolOpenAI22 September 20261.05M tokens$2.00 / $10.00Private43.9448
MiMo-V2.6-FlashXiaomi21 September 20261M tokens$0.14 / $0.28Open22.7338
Grok 4.7xAI21 September 2026500k tokens$2.00 / $6.00Private25.7646
MiMo V2.6 ProXiaomi21 September 20261M tokens$0.43 / $0.87Open34.8546
Step 5 PreviewStepFun18 September 20261M tokens$1.00 / $2.70Private33.3344
DeepSeek V4.1 FlashDeepSeek10 September 20261M tokens$0.30 / $1.20Open26.7739
Muse Spark 1.3 MaxMeta5 September 20261M tokens$1.25 / $4.25Private33.3348
GPT-6 AstraOpenAI3 September 20261M tokens$10.00 / $50.00Private59.0953
Qwen3.8 Max (0902)Alibaba2 September 2026983,616 tokens$2.00 / $6.00Private38.8945
Gemini 3.8 FlashGoogle2 September 20261M tokens$0.75 / $3.75Private19.7041
Claude Fable 5.1Anthropic1 September 20261M tokens$10.00 / $50.00Private52.0253
Hunyuan Hy4 PreviewTencent28 August 20261M tokens$0.83 / $2.50Open——
GLM 5.3 FlashZ.ai26 August 20261M tokens$0.15 / $0.50Open32.8342
Qwen3.8-Flash-NextAlibaba26 August 2026256k tokens$0.15 / $0.47Open25.2540
GLM 5.3Z.ai18 August 20261M tokens$1.40 / $4.40Open41.9245
Gemini 3.7 FlashGoogle13 August 20261M tokens$0.75 / $3.75Private13.6439
DeepSeek V4 ProDeepSeek13 August 20261M tokens$1.32 / $3.96Open14.1436
Qwen3.8 2.4T A95BAlibaba12 August 2026262k tokens$2.00 / $6.00Open11.1140
Grok 4.6xAI12 August 2026500,000 tokens$2.00 / $6.00Private17.1744
Muse Spark 1.2Meta5 August 20261,048,576 tokens$1.25 / $4.25Private7.0740
Qwen3.8 MaxAlibaba3 August 20261M tokens$2.00 / $6.00Open18.6940
Claude Opus 5Anthropic22 July 20261M tokens$5.00 / $25.00Private48.9951
Kimi K3Moonshot AI16 July 20261M tokens$3.00 / $15.00Open12.6344
InklingThinking Machines15 July 2026256k tokens$1.00 / $4.05Open1.0125
GPT-5.6 TerraOpenAI9 July 20261M tokens$2.00 / $12.00Private35.3542
GPT-5.6 SolOpenAI9 July 20261M tokens$4.00 / $20.00Private39.9047
GPT-5.6 LunaOpenAI9 July 20261M tokens$0.20 / $1.20Private11.6237
Grok 4.5xAI8 July 2026500,000 tokens$2.00 / $6.00Private10.6139
Claude Sonnet 5Anthropic30 June 20261M tokens$2.00 / $10.00Private14.1438
Claude Fable 5Anthropic9 June 20261M tokens$10.00 / $50.00Private42.4250
MiniMax M3MiniMax31 May 20261M tokens$0.60 / $2.40Open2.0229
Claude Opus 4.8Anthropic28 May 20261M tokens$5.00 / $25.00Private21.7242
Mistral Medium 3.5Mistral AI29 April 2026262k tokens$1.50 / $7.50Open0.0014
GPT-5.5OpenAI23 April 2026922,000 tokens$5.00 / $30.00Private14.6538
Claude Opus 4.7Anthropic16 April 20261M tokens$5.00 / $25.00Private—41
GPT-5.4OpenAI5 March 20261,050,000 tokens$2.50 / $15.00Private—39
Gemini 3.1 ProGoogle19 February 20261M tokens$2.00 / $12.00Private4.0430

Model pages distinguish lab specifications, evaluator-recorded API prices and hosted runtime facts.