Sources

Table may be scrolled horizontally on narrow displays.

SourceTypePublisherPublishedAccessed
Artificial Analysis Model LeaderboardLEADERBOARDArtificial AnalysisUnknown2026-07-13T04:53:32.160Z
Mistral-Small-4-119B-2603 Model CardMODEL_CARDMistral AIUnknown2026-07-12T18:25:17.133Z
MiniMax-M3 Model CardMODEL_CARDMiniMaxUnknown2026-07-12T18:21:16.253Z
Claude Fable 5 - Artificial AnalysisINDEPENDENT_EVALUATIONArtificial AnalysisUnknown2026-07-12T18:16:04.192Z
GPT-5.6 Luna (max) - Artificial AnalysisINDEPENDENT_EVALUATIONArtificial AnalysisUnknown2026-07-12T18:16:02.428Z
GPT-5.6 Terra (max) - Artificial AnalysisINDEPENDENT_EVALUATIONArtificial AnalysisUnknown2026-07-12T18:16:00.719Z
GPT-5.6 Sol (max) - Artificial AnalysisINDEPENDENT_EVALUATIONArtificial AnalysisUnknown2026-07-12T18:15:59.061Z
DeepSWE LeaderboardLEADERBOARDDataCurveUnknown2026-07-12T17:54:52.430Z
DeepSeek-V4-Flash Model CardMODEL_CARDDeepSeekUnknown2026-07-12T17:30:50.104Z
Composer 2 Technical ReportTECHNICAL_REPORTCursorUnknown2026-07-12T17:28:14.983Z
Claude Sonnet 5 - Artificial AnalysisINDEPENDENT_EVALUATIONArtificial AnalysisUnknown2026-07-12T17:25:14.579Z
Gemini 3.5 Flash (high) - Artificial AnalysisINDEPENDENT_EVALUATIONArtificial AnalysisUnknown2026-07-12T17:25:12.586Z
Grok 4.5 (high) - Artificial AnalysisINDEPENDENT_EVALUATIONArtificial AnalysisUnknown2026-07-12T17:25:10.868Z
Muse Spark 1.1 Evaluation ReportSYSTEM_CARDMetaUnknown2026-07-12T17:11:42.808Z
DeepSeek-V4-Pro Model CardMODEL_CARDDeepSeekUnknown2026-07-12T17:06:14.032Z
Gemini 3.1 Pro - Model CardMODEL_CARDGoogle DeepMindUnknown2026-07-12T16:45:21.774Z
GLM-5.2: Built for Long-Horizon TasksMODEL_CARDZ.ai (Zhipu)2026-06-132026-07-12T18:28:40.622Z
System Card: Claude Opus 4.8SYSTEM_CARDAnthropic2026-05-282026-07-12T17:16:28.964Z
Introducing Command A+PROVIDER_PAGECohere2026-05-202026-07-12T18:38:10.754Z
System Card: Claude Opus 4.7SYSTEM_CARDAnthropic2026-04-162026-07-12T16:45:19.987Z
Qwen3.5-397B-A17B Model CardMODEL_CARDQwen Team, Alibaba2026-02-162026-07-12T17:00:05.861Z