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
- GLM-4-9B-Chat-1MZ.ai (Zhipu AI) · 5 Jun 2024 · 1M context—in / 1M
- Palmyra Med 70B (32K)Writer · 3 Jun 2024 · 32.8K context—in / 1M
- Spark 4.0iFlytek · Jun 2024 · — context—in / 1M
- Falcon 2 11B VLMTechnology Innovation Institute (TII) · 21 May 2024 · 8.2K context—in / 1M
- Phi-3-mediumMicrosoft · 21 May 2024 · 131.1K context—in / 1M
- Phi-3-smallMicrosoft · 21 May 2024 · 131.1K context—in / 1M
- Granite 7B InstructIBM · 19 May 2024 · 4.1K context—in / 1M
- DeepSeek-V2-LiteDeepSeek · 16 May 2024 · 32.8K context—in / 1M
- DeepSeek-V2DeepSeek · 6 May 2024 · 131.1K context—in / 1M
- Hermes 2 Theta Llama 3 8BNous Research · 5 May 2024 · 8.2K context—in / 1M
- Aya 23 35BCohere · May 2024 · 8.2K context—in / 1M
- Aya 23 8BCohere · May 2024 · 8.2K context—in / 1M
- Falcon 2 11BTechnology Innovation Institute (TII) · May 2024 · 8.2K context—in / 1M
- K2-Chat (65B)MBZUAI (Institute of Foundation Models) · May 2024 · 8.2K context—in / 1M
- Yi-1.5-34B-Chat01.AI · May 2024 · 4.1K context—in / 1M
- Yi-1.5-6B-Chat01.AI · May 2024 · 4.1K context—in / 1M
- Yi-1.5-9B-Chat01.AI · May 2024 · 4.1K context—in / 1M
- Yi-Large01.AI · May 2024 · — context—in / 1M
- Hermes 2 Pro Llama 3 8BNous Research · 30 Apr 2024 · 8.2K context—in / 1M
- Qwen1.5-110B-ChatAlibaba Group · 25 Apr 2024 · 32.8K context—in / 1M
- Phi-3-miniMicrosoft · 23 Apr 2024 · 131.1K context—in / 1M
- Llama 3 70BMeta · 18 Apr 2024 · 8.2K context—in / 1M
- Llama 3 8BMeta · 18 Apr 2024 · 8.2K context—in / 1M
- Llama Guard 2Meta · 18 Apr 2024 · 8.2K context—in / 1M
- OLMo 1.7 7B (0424)Allen Institute for AI (Ai2) · 17 Apr 2024 · 2K context—in / 1M
- RecurrentGemma 2BGoogle DeepMind · 9 Apr 2024 · — context—in / 1M
- StableLM 2 12BStability AI · 8 Apr 2024 · 4.1K context—in / 1M
- Command R+ (04-2024)Cohere · 4 Apr 2024 · 128K context$3.00in / 1M
- Qwen1.5-32B-ChatAlibaba Group · 2 Apr 2024 · 32.8K context—in / 1M
- MiniCPM-1BModelBest · Apr 2024 · 4.1K context—in / 1M
- MiniCPM-2B-128kModelBest · Apr 2024 · 65.5K context—in / 1M
- MiniCPM-MoE-8x2BModelBest · Apr 2024 · 4.1K context—in / 1M
- OpenELM 1.1BApple · Apr 2024 · 2K context—in / 1M
- OpenELM 270MApple · Apr 2024 · 2K context—in / 1M
- OpenELM 3BApple · Apr 2024 · 2K context—in / 1M
- OpenELM 450MApple · Apr 2024 · 2K context—in / 1M
- SenseNova 5.0SenseTime · Apr 2024 · — context—in / 1M
- Snowflake Arctic InstructSnowflake · Apr 2024 · 4.1K context—in / 1M
- Jamba v0.1AI21 Labs · 28 Mar 2024 · 256K context—in / 1M
- Qwen1.5-MoE-A2.7B-ChatAlibaba Group · 28 Mar 2024 · 32.8K context—in / 1M
- DBRX InstructDatabricks · 27 Mar 2024 · — context—in / 1M
- Command R (03-2024)Cohere · 11 Mar 2024 · 128K context$0.50in / 1M
- Hermes 2 Pro Mistral 7BNous Research · 11 Mar 2024 · — context—in / 1M
- EvoLLM-JP-v1-10BSakana AI · Mar 2024 · 32.8K context—in / 1M
- EvoLLM-JP-v1-7BSakana AI · Mar 2024 · 32.8K context—in / 1M
- EvoVLM-JP-v1-7BSakana AI · Mar 2024 · 32.8K context—in / 1M
- Yi-9B01.AI · Mar 2024 · 4.1K context—in / 1M
- Nous Hermes 2 Mistral 7B DPONous Research · 18 Feb 2024 · — context—in / 1M
- Qwen1.5-0.5B-ChatAlibaba Group · 5 Feb 2024 · 32.8K context—in / 1M
- Qwen1.5-1.8B-ChatAlibaba Group · 5 Feb 2024 · 32.8K context—in / 1M