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
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· 128K and up
Input price
Weights· Proprietary
Reasoning
- LongCat-2.5-PreviewMeituan · 25 Sep 2026 · 1M context—in / 1M
- Solar Mini 4Upstage · 22 Sep 2026 · 524.3K context$0.10in / 1M
- Grok 4.7SpaceXAI (xAI) · 21 Sep 2026 · 500K context$2.00in / 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
- Mercury 2.5Inception · 8 Sep 2026 · 260K context$0.04in / 1M
- Step 5 PreviewStepFun · Sep 2026 · 1M context$1.00in / 1M
- Qwen3.8-FlashAlibaba Group · 26 Aug 2026 · 1M context$0.15in / 1M
- Grok 4.6SpaceXAI (xAI) · 12 Aug 2026 · 500K context$2.00in / 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
- SenseNova 6.8 Flash LiteSenseTime · Aug 2026 · 262.1K context—in / 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
- 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
- FuguSakana AI · 15 Jun 2026 · 1M context—in / 1M
- Fugu UltraSakana AI · 15 Jun 2026 · 1M context$5.00in / 1M
- MAI-Thinking-1Microsoft · 2 Jun 2026 · 256K context—in / 1M
- Qwen3.7-PlusAlibaba Group · 1 Jun 2026 · 1M context$0.40in / 1M
- Qwen3.7-MaxAlibaba Group · 20 May 2026 · 1M context$2.50in / 1M
- Gemini Deep Research MaxGoogle DeepMind · 21 Apr 2026 · 1M context—in / 1M
- Grok 4.3SpaceXAI (xAI) · 17 Apr 2026 · 1M context$1.25in / 1M
- Qwen3.6-FlashAlibaba Group · 16 Apr 2026 · 1M context$0.25in / 1M
- Qwen3.6-Max-PreviewAlibaba Group · 14 Apr 2026 · 262.1K context$1.30in / 1M
- Qwen3.6-PlusAlibaba Group · 2 Apr 2026 · 1M context$0.50in / 1M
- MiMo-V2-OmniXiaomi · 18 Mar 2026 · 262.1K context—in / 1M
- MiMo-V2-ProXiaomi · 18 Mar 2026 · 1M context—in / 1M
- GLM-5-TurboZ.ai (Zhipu AI) · 15 Mar 2026 · 204.8K context—in / 1M
- Grok 4.20 Multi-AgentSpaceXAI (xAI) · 9 Mar 2026 · 1M context$1.25in / 1M
- Mistral Moderation 2Mistral AI · 1 Mar 2026 · 131.1K context—in / 1M
- Mercury 2Inception · 24 Feb 2026 · 128K context$0.25in / 1M
- Qwen3.5-FlashAlibaba Group · 23 Feb 2026 · 1M context$0.10in / 1M
- Qwen3.5-PlusAlibaba Group · 15 Feb 2026 · 1M context$0.40in / 1M
- Doubao-Seed-2.0-CodeByteDance · 14 Feb 2026 · 262.1K context—in / 1M
- Doubao-Seed-2.0-liteByteDance · 14 Feb 2026 · 262.1K context—in / 1M
- Doubao-Seed-2.0-miniByteDance · 14 Feb 2026 · 262.1K context—in / 1M
- Doubao-Seed-2.0-proByteDance · 14 Feb 2026 · 262.1K context—in / 1M
- Grok 4.20SpaceXAI (xAI) · Feb 2026 · 1M context$1.25in / 1M
- Solar Pro 3Upstage · 26 Jan 2026 · 128K context$0.15in / 1M
- Gemini Deep ResearchGoogle DeepMind · 11 Dec 2025 · 1M context—in / 1M
- Qwen3-MaxAlibaba Group · 5 Sep 2025 · 262.1K context$1.20in / 1M
- GLM-4.5-FlashZ.ai (Zhipu AI) · 28 Jul 2025 · 131.1K context$0.00in / 1M
- Qwen-FlashAlibaba Group · 28 Jul 2025 · 1M context$0.05in / 1M
- Sonar Deep ResearchPerplexity · Mar 2025 · 128K context$2.00in / 1M
- Sonar Reasoning ProPerplexity · Mar 2025 · 128K context$2.00in / 1M
- SonarPerplexity · Jan 2025 · 128K context$1.00in / 1M
- Sonar ProPerplexity · Jan 2025 · 200K context$3.00in / 1M