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
Input price
Weights
Reasoning· Not reasoning
- MobileLLM 125MMeta · 30 Oct 2024 · — context—in / 1M
- MobileLLM 350MMeta · 30 Oct 2024 · — context—in / 1M
- MobileLLM 600MMeta · 30 Oct 2024 · — context—in / 1M
- Aya Expanse 32BCohere · 24 Oct 2024 · 128K context$0.50in / 1M
- Gemma-APS 2BGoogle DeepMind · 15 Oct 2024 · — context—in / 1M
- Gemma-APS 7BGoogle DeepMind · 15 Oct 2024 · — context—in / 1M
- Inflection 3.0 PiInflection AI · 7 Oct 2024 · — context—in / 1M
- Inflection 3.0 ProductivityInflection AI · 7 Oct 2024 · — context—in / 1M
- Mistral-NeMo-Minitron 8B InstructNVIDIA · 2 Oct 2024 · 8.2K context—in / 1M
- SuperNova-Medius (14B)Arcee AI · 2 Oct 2024 · — context—in / 1M
- Granite 3.0 1B-A400M InstructIBM · Oct 2024 · 4.1K context—in / 1M
- Granite 3.0 2B InstructIBM · Oct 2024 · 4.1K context—in / 1M
- Granite 3.0 3B-A800M InstructIBM · Oct 2024 · 4.1K context—in / 1M
- Granite 3.0 8B InstructIBM · Oct 2024 · 4.1K context—in / 1M
- Granite Guardian 3.0 (2B, 8B)IBM · Oct 2024 · — context—in / 1M
- Llama-3.1-Nemotron-70B-InstructNVIDIA · Oct 2024 · 131.1K context—in / 1M
- Sarvam-1Sarvam AI · Oct 2024 · 8.2K context—in / 1M
- Yi-Lightning01.AI · Oct 2024 · — context—in / 1M
- Llama 3.2 11B VisionMeta · 25 Sep 2024 · 131.1K context—in / 1M
- Llama 3.2 1BMeta · 25 Sep 2024 · 131.1K context—in / 1M
- Llama 3.2 3BMeta · 25 Sep 2024 · 131.1K context—in / 1M
- Llama 3.2 90B VisionMeta · 25 Sep 2024 · 131.1K context—in / 1M
- Llama Guard 3 11B VisionMeta · 25 Sep 2024 · 131.1K context—in / 1M
- Llama Guard 3 1BMeta · 25 Sep 2024 · 131.1K context—in / 1M
- Qwen-Math-TurboAlibaba Group · 19 Sep 2024 · — context—in / 1M
- Qwen2.5-0.5B-InstructAlibaba Group · 19 Sep 2024 · 32.8K context—in / 1M
- Qwen2.5-1.5B-InstructAlibaba Group · 19 Sep 2024 · 32.8K context—in / 1M
- Qwen2.5-14B-InstructAlibaba Group · 19 Sep 2024 · 131.1K context—in / 1M
- Qwen2.5-32B-InstructAlibaba Group · 19 Sep 2024 · 131.1K context—in / 1M
- Qwen2.5-3B-InstructAlibaba Group · 19 Sep 2024 · 32.8K context—in / 1M
- Qwen2.5-72B-InstructAlibaba Group · 19 Sep 2024 · 131.1K context—in / 1M
- Qwen2.5-7B-InstructAlibaba Group · 19 Sep 2024 · 131.1K context—in / 1M
- Qwen2.5-Math-1.5B-InstructAlibaba Group · 19 Sep 2024 · 4.1K context—in / 1M
- Qwen2.5-Math-72B-InstructAlibaba Group · 19 Sep 2024 · 4.1K context—in / 1M
- Qwen2.5-Math-7B-InstructAlibaba Group · 19 Sep 2024 · 4.1K context—in / 1M
- DataGemma RAG 27BGoogle DeepMind · 12 Sep 2024 · — context—in / 1M
- DataGemma RIG 27BGoogle DeepMind · 12 Sep 2024 · — context—in / 1M
- Llama-3.1-SuperNova-Lite (8B)Arcee AI · 10 Sep 2024 · 131.1K context—in / 1M
- Nemotron-Mini-4B-InstructNVIDIA · 10 Sep 2024 · 4.1K context—in / 1M
- Solar Pro PreviewUpstage · 10 Sep 2024 · 4.1K context—in / 1M
- DeepSeek-V2.5DeepSeek · 5 Sep 2024 · 131.1K context—in / 1M
- Llama-3.1-Nemotron-51B-InstructNVIDIA · Sep 2024 · 131.1K context—in / 1M
- MiniCPM3-4BModelBest · Sep 2024 · 32.8K context—in / 1M
- OLMoE 1B-7B (0924) InstructAllen Institute for AI (Ai2) · Sep 2024 · 4.1K context—in / 1M
- PLaMo-100B (base)Preferred Networks · Sep 2024 · — context—in / 1M
- reader-lm 0.5BJina AI · Sep 2024 · — context—in / 1M
- reader-lm 1.5BJina AI · Sep 2024 · — context—in / 1M
- Command R (08-2024)Cohere · 30 Aug 2024 · 128K context$0.15in / 1M
- Command R+ (08-2024)Cohere · 30 Aug 2024 · 128K context$2.50in / 1M
- Palmyra Creative (122B)Writer · 28 Aug 2024 · 131.1K context—in / 1M