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
Context· 1M and up
Input price
Weights· Open weights
Reasoning· Reasoning
- MiMo-V2.6-FlashXiaomi · 21 Sep 2026 · 1M context—in / 1M
- MiMo-V2.6-ProXiaomi · 21 Sep 2026 · 1M context—in / 1M
- DeepSeek-V4.1-FlashDeepSeek · 10 Sep 2026 · 1M context$0.30in / 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
- 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
- Nemotron 3.5 Lightning 30B-A3BNVIDIA · 11 Aug 2026 · 1M context—in / 1M
- Laguna S 2.1Poolside · 21 Jul 2026 · 1M context—in / 1M
- Kimi K3Moonshot AI · 16 Jul 2026 · 1M context$3.00in / 1M
- Solar Open 2 (250B)Upstage · 8 Jul 2026 · 1M context—in / 1M
- LongCat-2.0Meituan · 30 Jun 2026 · 1M context—in / 1M
- GLM-5.2Z.ai (Zhipu AI) · 16 Jun 2026 · 1M context$1.40in / 1M
- Nemotron 3 Ultra 550B-A55BNVIDIA · 4 Jun 2026 · 1M context—in / 1M
- MiniMax-M3MiniMax · 1 Jun 2026 · 1M context$0.30in / 1M
- DeepSeek-V4-FlashDeepSeek · 24 Apr 2026 · 1M context—in / 1M
- DeepSeek-V4-ProDeepSeek · 24 Apr 2026 · 1M context$1.32in / 1M
- MiMo-V2.5Xiaomi · 22 Apr 2026 · 1M context—in / 1M
- MiMo-V2.5-ProXiaomi · 22 Apr 2026 · 1M context—in / 1M
- Nemotron 3 Super 120B-A12BNVIDIA · 11 Mar 2026 · 1M context—in / 1M
- MiniMax-M1MiniMax · 16 Jun 2025 · 1M context—in / 1M