Explore performance across multiple benchmarks for a single model.
Filter
Accessibility
Open weights (138)
Developer
OpenAIGoogle DeepMindAlibabaMeta AIAnthropicDeepSeekMistral AIMicrosoftxAITsinghua UniversityNVIDIAZ.ai (Zhipu AI)01.AIHugging FacePeking UniversityTechnology Innovation InstituteBaichuanMiniMaxMoonshotUniversity of WashingtonShanghai AI LabAmazonEleutherAIServiceNowBigCodeArcee AIAllen Institute for AIDatabricksShanghai Jiao Tong UniversityCohereDeepMindMosaicMLUniversity of California (UC) BerkeleyNous ResearchUniversity of Illinois Urbana-Champaign (UIUC)CUHK Shenzhen Research InstituteGoogle ResearchStability AIInflection AISalesforceLAIONCerebras SystemsBigSciencePrime IntellectNew York University (NYU)Large Model Systems OrganizationPerplexityByteDanceSenseTimeNanjing UniversityFudan UniversityChinese University of Hong Kong (CUHK)Massachusetts Institute of Technology (MIT)University of California San DiegoReka AISalesforce Research
256 results
GPT-5.4 Pro
OpenAI
2026-03-06
Closed weights
158ECI
Gemini 3.1 Pro
Google DeepMind
2026-02-20
Closed weights
157ECI
GPT-5.4
OpenAI
2026-03-06
Closed weights
155ECI
Claude Opus 4.6
Anthropic
2026-02-06
Closed weights
155ECI
Gemini 3 Pro
Google DeepMind
2025-11-19
Closed weights
153ECI
GPT-5.2
OpenAI
2025-12-12
Closed weights
153ECI
Claude Sonnet 4.6
Anthropic
2026-02-18
Closed weights
152ECI
Gemini 3 Flash
Google DeepMind
2025-12-18
Closed weights
152ECI
GPT-5
OpenAI
2025-08-08
Closed weights
150ECI
GPT-5 Pro
OpenAI
2025-10-08
Closed weights
150ECI
Feedback
Have a question? Noticed something wrong? Let us know.