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· 128K and up
Input price
Weights
Reasoning
- GPT AudioOpenAI · 28 Aug 2025 · 128K context$2.50in / 1M
- Command A ReasoningCohere · 21 Aug 2025 · 256K context$2.50in / 1M
- DeepSeek-V3.1DeepSeek · 21 Aug 2025 · 131.1K context—in / 1M
- NVIDIA Nemotron Nano 12B v2NVIDIA · 21 Aug 2025 · 131.1K context—in / 1M
- Llama 3.1 Nemotron Safety Guard 8B v3NVIDIA · 20 Aug 2025 · 131.1K context—in / 1M
- Seed-OSS-36B-InstructByteDance · 20 Aug 2025 · 524.3K context—in / 1M
- NVIDIA Nemotron Nano 9B v2NVIDIA · 12 Aug 2025 · 131.1K context—in / 1M
- GPT-5OpenAI · 7 Aug 2025 · 400K context$1.25in / 1M
- GPT-5 miniOpenAI · 7 Aug 2025 · 400K context$0.25in / 1M
- GPT-5 nanoOpenAI · 7 Aug 2025 · 400K context$0.05in / 1M
- GPT-5 ProOpenAI · 7 Aug 2025 · 400K context$15.00in / 1M
- Qwen3-4B-Instruct-2507Alibaba Group · 6 Aug 2025 · 262.1K context—in / 1M
- Qwen3-4B-Thinking-2507Alibaba Group · 6 Aug 2025 · 262.1K context—in / 1M
- gpt-oss-120bOpenAI · 5 Aug 2025 · 131.1K context—in / 1M
- gpt-oss-20bOpenAI · 5 Aug 2025 · 131.1K context—in / 1M
- Baichuan-M2-32BBaichuan Intelligence · Aug 2025 · 131.1K context—in / 1M
- Hermes 4 405BNous Research · Aug 2025 · 131.1K context—in / 1M
- Hermes 4 70BNous Research · Aug 2025 · 131.1K context—in / 1M
- Hunyuan-0.5B-InstructTencent · Aug 2025 · 262.1K context—in / 1M
- Hunyuan-1.8B-InstructTencent · Aug 2025 · 262.1K context—in / 1M
- Hunyuan-4B-InstructTencent · Aug 2025 · 262.1K context—in / 1M
- Keye-VL-1.5-8BKuaishou · Aug 2025 · 131.1K context—in / 1M
- Command A VisionCohere · 31 Jul 2025 · 128K context$2.50in / 1M
- Qwen3-30B-A3B-Thinking-2507Alibaba Group · 31 Jul 2025 · 262.1K context—in / 1M
- Qwen3-Coder-30B-A3B-InstructAlibaba Group · 31 Jul 2025 · 262.1K context$0.45in / 1M
- Codestral 25.08Mistral AI · 30 Jul 2025 · 131.1K context$0.30in / 1M
- Qwen3-30B-A3B-Instruct-2507Alibaba Group · 30 Jul 2025 · 262.1K context$0.20in / 1M
- GLM-4.5Z.ai (Zhipu AI) · 28 Jul 2025 · 131.1K context$0.60in / 1M
- GLM-4.5-AirZ.ai (Zhipu AI) · 28 Jul 2025 · 131.1K context$0.20in / 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
- Qwen3-Coder-FlashAlibaba Group · 28 Jul 2025 · 1M context$0.30in / 1M
- Llama 3.3 Nemotron Super 49B v1.5NVIDIA · 25 Jul 2025 · 131.1K context—in / 1M
- Qwen3-235B-A22B-Thinking-2507Alibaba Group · 25 Jul 2025 · 262.1K context$0.23in / 1M
- Qwen3-Coder-480B-A35B-InstructAlibaba Group · 22 Jul 2025 · 262.1K context$1.50in / 1M
- Qwen3-Coder-PlusAlibaba Group · 22 Jul 2025 · 1M context$1.00in / 1M
- Qwen3-235B-A22B-Instruct-2507Alibaba Group · 21 Jul 2025 · 262.1K context$0.23in / 1M
- EXAONE-4.0-32BLG AI Research · 15 Jul 2025 · 131.1K context—in / 1M
- Kimi K2Moonshot AI · 11 Jul 2025 · 262.1K context—in / 1M
- MedGemma 27B (multimodal)Google DeepMind · 9 Jul 2025 · 131.1K context—in / 1M
- A.X 4.0SK Telecom · Jul 2025 · 131.1K context—in / 1M
- HyperCLOVAX-SEED-Think-14BNaver · Jul 2025 · 131.1K context—in / 1M
- Jamba 1.7 LargeAI21 Labs · Jul 2025 · 256K context$2.00in / 1M
- KAT-V1-40BKuaishou · Jul 2025 · 131.1K context—in / 1M
- ERNIE-4.5-0.3BBaidu · 30 Jun 2025 · 131.1K context—in / 1M
- ERNIE-4.5-21B-A3BBaidu · 30 Jun 2025 · 131.1K context—in / 1M
- ERNIE-4.5-300B-A47BBaidu · 30 Jun 2025 · 131.1K context—in / 1M
- ERNIE-4.5-VL-28B-A3BBaidu · 30 Jun 2025 · 131.1K context—in / 1M
- ERNIE-4.5-VL-424B-A47BBaidu · 30 Jun 2025 · 131.1K context—in / 1M
- Hunyuan-A13B-InstructTencent · 27 Jun 2025 · 262.1K context—in / 1M