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
Context· 128K and up
Input price
Weights· Open weights
Reasoning
- Qwen3-8BAlibaba Group · 29 Apr 2025 · 131.1K context$0.18in / 1M
- Cosmos Reason1 7BNVIDIA · 18 Apr 2025 · 128K context—in / 1M
- MAI-DS-R1Microsoft · 16 Apr 2025 · 163.8K context—in / 1M
- Nemotron-H 4B Instruct 128KNVIDIA · 15 Apr 2025 · 131.1K context—in / 1M
- GLM-4-32B-0414Z.ai (Zhipu AI) · 14 Apr 2025 · 131.1K context$0.10in / 1M
- GLM-Z1-Rumination-32B-0414Z.ai (Zhipu AI) · 14 Apr 2025 · 131.1K context—in / 1M
- Kimi-VL-A3B-InstructMoonshot AI · 10 Apr 2025 · 131.1K context—in / 1M
- Kimi-VL-A3B-ThinkingMoonshot AI · 10 Apr 2025 · 131.1K context—in / 1M
- Llama 3.1 Nemotron Ultra 253B v1NVIDIA · 7 Apr 2025 · 131.1K context—in / 1M
- Llama 4 MaverickMeta · 5 Apr 2025 · 1M context—in / 1M
- Llama 4 ScoutMeta · 5 Apr 2025 · 10M context—in / 1M
- Granite 3.3 2B InstructIBM · Apr 2025 · 131.1K context—in / 1M
- Granite 3.3 8B InstructIBM · Apr 2025 · 131.1K context—in / 1M
- HyperCLOVAX-SEED-Vision-Instruct-3BNaver · Apr 2025 · 131.1K context—in / 1M
- UI-TARS-1.5-7BByteDance · Apr 2025 · 128K context—in / 1M
- Qwen2.5-VL-32B-InstructAlibaba Group · 25 Mar 2025 · 128K context—in / 1M
- Command ACohere · 13 Mar 2025 · 256K context$2.50in / 1M
- Gemma 3 12BGoogle DeepMind · 10 Mar 2025 · 131.1K context—in / 1M
- Gemma 3 27BGoogle DeepMind · 10 Mar 2025 · 131.1K context—in / 1M
- Gemma 3 4BGoogle DeepMind · 10 Mar 2025 · 131.1K context—in / 1M
- QwQ-32BAlibaba Group · 6 Mar 2025 · 131.1K context—in / 1M
- Llama 3.1 Nemotron Nano 8B v1NVIDIA · Mar 2025 · 131.1K context—in / 1M
- Llama 3.3 Nemotron Super 49B v1NVIDIA · Mar 2025 · 131.1K context—in / 1M
- Command R7B ArabicCohere · 27 Feb 2025 · 128K context$0.04in / 1M
- Phi-4-miniMicrosoft · 26 Feb 2025 · 131.1K context$0.07in / 1M
- Phi-4-multimodalMicrosoft · 26 Feb 2025 · 131.1K context$0.08in / 1M
- DeepHermes 3 Llama 3 8B PreviewNous Research · 12 Feb 2025 · 131.1K context—in / 1M
- Llama 3.1 Tulu 3.1 8BAllen Institute for AI (Ai2) · 7 Feb 2025 · 131.1K context—in / 1M
- Granite 3.2 2B InstructIBM · Feb 2025 · 131.1K context—in / 1M
- Granite 3.2 8B InstructIBM · Feb 2025 · 131.1K context—in / 1M
- Granite Vision 3.2 2BIBM · Feb 2025 · 131.1K context—in / 1M
- Qwen2.5-VL-3B-InstructAlibaba Group · 28 Jan 2025 · 128K context—in / 1M
- Qwen2.5-VL-72B-InstructAlibaba Group · 28 Jan 2025 · 128K context—in / 1M
- Qwen2.5-VL-7B-InstructAlibaba Group · 28 Jan 2025 · 128K context—in / 1M
- Qwen2.5-14B-Instruct-1MAlibaba Group · 27 Jan 2025 · 1M context—in / 1M
- Qwen2.5-7B-Instruct-1MAlibaba Group · 27 Jan 2025 · 1M context—in / 1M
- DeepSeek-R1DeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Llama-70BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Llama-8BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Qwen-1.5BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Qwen-14BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Qwen-32BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Qwen-7BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-ZeroDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- MiniMax-Text-01MiniMax · 15 Jan 2025 · 1M context—in / 1M
- MiniMax-VL-01MiniMax · 15 Jan 2025 · 1M context—in / 1M
- Hunyuan-7B-InstructTencent · Jan 2025 · 262.1K context—in / 1M
- Llama 3.1 Tulu 3 405BAllen Institute for AI (Ai2) · Jan 2025 · 131.1K context—in / 1M
- ReaderLM-v2Jina AI · Jan 2025 · 512K context—in / 1M
- DeepSeek-V3DeepSeek · 26 Dec 2024 · 131.1K context—in / 1M