Model release timeline
8 release months, 4 quarters, 33 models. Dates come from the release field on each model page; some vendors only publish a month.
2026 Q4
17 models2026-11-09Claude Fable 5.2Anthropic65 v52026-11-17GPT-6.2 AstraOpenAI62 v52026-11-17GPT-6.2 SolOpenAI57 v52026-11-18Gemini 4 NeonGoogle61 v52026-11-12Gemini 4 HydrogenGoogle54 v52026-11-16Qwen4 MaxAlibaba Qwen42.9 v52026-11-04Tencent Hy4Tencent Hunyuan34.6 v52026-10Claude Opus 5.5Anthropic59.1 v52026-10-26GPT-6.1 TerraOpenAI51.3 v52026-10-28Gemini 4 CarbonGoogle60 v52026-10-13Gemini 4 ArgonGoogle50.4 v52026-10-29Mistral Large 4Mistral26 v52026-10Muse WonderMeta44 v52026-10-12Muse Wonder FullMeta50 v52026-10-23Kimi K3.1 ProMoonshot AI46 v52026-10-17DeepSeek V4.1 FlashDeepSeek33 v52026-10-26MiniMax M3.1 FlashMiniMax29 v5
2026 Q3
12 models2026-09Claude Sonnet 5.5Anthropic54.5 v52026-09Claude Haiku 5.5Anthropic36 v52026-09Grok 4.7xAI35.5 v52026-09GLM-5.3 FlashZ.ai28 v52026-09-21MiMo-V2.6 ProXiaomi30 v52026-09Qwen3.8 27BAlibaba Qwen20 v52026-09Step 5 PreviewStepFun29 v52026-08Gemini 3.8 FlashGoogle31 v52026-08-13DeepSeek V4 ProDeepSeek23 v52026-08GLM-5.3Z.ai32 v52026-07GPT-6 LunaOpenAI28 v52026-07-27Kimi K3Moonshot AI43.6 v4.3.2
2026 Q2
3 models2025 Q3
1 modelsData sources & methodology
Full methodology & sources →Every number on this page comes from published evaluations. We run no tests of our own and accept no vendor-submitted scores. Main sources:
Evaluation data in the wider industry also comes from public datasets, leaderboard platforms and their evaluation harnesses, private in-house sets, production logs and user feedback, and synthetic data. This site's current rankings use only the parts that are public, independently checkable and clearly defined.