Updated daily at 05:00 UTC
Models
AI models
1521 current models, newest first. Each links to its benchmark results, with who ran them.
Best by specialty
Independent and third-party results only · method category-2026-09-29.1
Not ranked yet
Too few independent or third-party results to rank:
Scientific reasoning, Mathematics, Long context, OCR & documents, Law, Medicine & health, Finance, Multilingual, Instruction following, Writing, Speech & audio.
All current models
Best for
- Knowledge & reasoning
- Scientific reasoning
- Mathematics
- Coding & software engineering
- Agentic tool use
- Computer & browser use
- Professional knowledge work
- Long context
- Vision & multimodal understanding
- OCR & documents
- Law
- Medicine & health
- Finance
- Multilingual
- Factuality & hallucination
- Instruction following
- Writing
- Speech & audio
- Human preference
Kind· Language
Context
Input price
Weights
Reasoning· Reasoning
- LongCat-2.5-PreviewMeituan · 25 Sep 2026 · 1M context—in / 1M
- Grok 4.7SpaceXAI (xAI) · 21 Sep 2026 · 500K context$2.00in / 1M
- MiMo-V2.6-FlashXiaomi · 21 Sep 2026 · 1M context—in / 1M
- MiMo-V2.6-ProXiaomi · 21 Sep 2026 · 1M context—in / 1M
- Doubao-Seed-2.1-liteByteDance · 15 Sep 2026 · 262.1K context—in / 1M
- Fugu MaxSakana AI · 11 Sep 2026 · 1M context$2.00in / 1M
- Fugu Ultra v2Sakana AI · 11 Sep 2026 · 1M context$5.00in / 1M
- DeepSeek-V4.1-FlashDeepSeek · 10 Sep 2026 · 1M context$0.30in / 1M
- Mercury 2.5Inception · 8 Sep 2026 · 260K context$0.04in / 1M
- K2-Horizon-0.9BMBZUAI (Institute of Foundation Models) · 3 Sep 2026 · 131.1K context—in / 1M
- K2-Horizon-3.7BMBZUAI (Institute of Foundation Models) · 3 Sep 2026 · 524.3K context—in / 1M
- K2-Horizon-32BMBZUAI (Institute of Foundation Models) · 3 Sep 2026 · 524.3K context—in / 1M
- K2-Horizon-375B-A23BMBZUAI (Institute of Foundation Models) · 3 Sep 2026 · 524.3K context—in / 1M
- K2-Horizon-7BMBZUAI (Institute of Foundation Models) · 3 Sep 2026 · 524.3K context—in / 1M
- MiniCPM5-2BModelBest · Sep 2026 · 131.1K context—in / 1M
- Step 5 PreviewStepFun · Sep 2026 · 1M context$1.00in / 1M
- Hy4 previewTencent · 28 Aug 2026 · 1M context—in / 1M
- GLM-5.3-FlashZ.ai (Zhipu AI) · 26 Aug 2026 · 1M context$0.15in / 1M
- Qwen3.8-FlashAlibaba Group · 26 Aug 2026 · 1M context$0.15in / 1M
- Qwen3.8-Flash-NextAlibaba Group · 26 Aug 2026 · 262.1K context—in / 1M
- DeepSeek-V4-Flash-Vision-ExpDeepSeek · 21 Aug 2026 · 1M context—in / 1M
- GLM-5.3Z.ai (Zhipu AI) · 18 Aug 2026 · 1M context$1.40in / 1M
- Qwen3.8-27BAlibaba Group · 14 Aug 2026 · 262.1K context$0.50in / 1M
- Grok 4.6SpaceXAI (xAI) · 12 Aug 2026 · 500K context$2.00in / 1M
- Qwen3.8-2.4T-A95BAlibaba Group · 12 Aug 2026 · 262.1K context$2.00in / 1M
- Nemotron 3.5 Lightning 30B-A3BNVIDIA · 11 Aug 2026 · 1M context—in / 1M
- Solar Pro 4Upstage · 6 Aug 2026 · 524.3K context$0.30in / 1M
- Sakana NamazuSakana AI · 3 Aug 2026 · 262.1K context$0.95in / 1M
- Qwen3.8-MaxAlibaba Group · 2 Aug 2026 · 1M context$2.00in / 1M
- Ling-3.0-tinyAnt Group · Aug 2026 · 131.1K context—in / 1M
- SenseNova 6.8 Flash LiteSenseTime · Aug 2026 · 262.1K context—in / 1M
- K-EXAONE-2.0-750B-A37BLG AI Research · 31 Jul 2026 · 262.1K context—in / 1M
- Kimi K3Moonshot AI · 16 Jul 2026 · 1M context$3.00in / 1M
- Qwen3.7-FlashAlibaba Group · 15 Jul 2026 · 1M context$0.03in / 1M
- Grok 4.5SpaceXAI (xAI) · 8 Jul 2026 · 500K context$2.00in / 1M
- Solar Open 2 (250B)Upstage · 8 Jul 2026 · 1M context—in / 1M
- Hy3Tencent · 6 Jul 2026 · 262.1K context—in / 1M
- A.X K2SK Telecom · Jul 2026 · 262.1K context—in / 1M
- LongCat-2.0Meituan · 30 Jun 2026 · 1M context—in / 1M
- Doubao-Seed-2.1-proByteDance · 28 Jun 2026 · 262.1K context—in / 1M
- Doubao-Seed-2.1-turboByteDance · 28 Jun 2026 · 262.1K context—in / 1M
- GLM-5.2Z.ai (Zhipu AI) · 16 Jun 2026 · 1M context$1.40in / 1M
- FuguSakana AI · 15 Jun 2026 · 1M context—in / 1M
- Fugu UltraSakana AI · 15 Jun 2026 · 1M context$5.00in / 1M
- Kimi K2.7 CodeMoonshot AI · 12 Jun 2026 · 262.1K context$0.95in / 1M
- North Mini Code 1.0Cohere · 9 Jun 2026 · 256K context—in / 1M
- Nemotron 3 Ultra 550B-A55BNVIDIA · 4 Jun 2026 · 1M context—in / 1M
- MAI-Thinking-1Microsoft · 2 Jun 2026 · 256K context—in / 1M
- MiniMax-M3MiniMax · 1 Jun 2026 · 1M context$0.30in / 1M
- Qwen3.7-PlusAlibaba Group · 1 Jun 2026 · 1M context$0.40in / 1M