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· Vision-language
Context
Input price
Weights
Reasoning· Reasoning
- GPT-5.4OpenAI · 5 Mar 2026 · 1.1M context$2.50in / 1M
- GPT-5.4 ProOpenAI · 5 Mar 2026 · 1.1M context$30.00in / 1M
- Gemini 3.1 Flash-LiteGoogle DeepMind · 3 Mar 2026 · 1M context$0.25in / 1M
- Gemini 3.1 ProGoogle DeepMind · 19 Feb 2026 · 1M context$2.00in / 1M
- Claude Sonnet 4.6Anthropic · 17 Feb 2026 · 1M context$3.00in / 1M
- Claude Opus 4.6Anthropic · 5 Feb 2026 · 1M context$5.00in / 1M
- Intern-S1-ProShanghai AI Laboratory · Feb 2026 · 262.1K context—in / 1M
- Phi-4-reasoning-vision-15BMicrosoft · Jan 2026 · 32.8K context—in / 1M
- SenseNova-MARS-32BSenseTime · Jan 2026 · 262.1K context—in / 1M
- Step3-VL-10BStepFun · Jan 2026 · 65.5K context—in / 1M
- Gemini 3 FlashGoogle DeepMind · 17 Dec 2025 · 1M context$0.50in / 1M
- Cosmos Reason2 2BNVIDIA · 12 Dec 2025 · — context—in / 1M
- Cosmos Reason2 8BNVIDIA · 12 Dec 2025 · — context—in / 1M
- GPT-5.2OpenAI · 11 Dec 2025 · 400K context$1.75in / 1M
- GPT-5.2 ProOpenAI · 11 Dec 2025 · 400K context$21.00in / 1M
- GLM-4.6VZ.ai (Zhipu AI) · 8 Dec 2025 · 131.1K context$0.30in / 1M
- GLM-4.6V-FlashZ.ai (Zhipu AI) · 8 Dec 2025 · 131.1K context$0.00in / 1M
- Amazon Nova 2 Pro (preview)Amazon · 3 Dec 2025 · 1M context—in / 1M
- Amazon Nova 2 LiteAmazon · 2 Dec 2025 · 1M context$0.33in / 1M
- SenseNova-MARS-8BSenseTime · Dec 2025 · 262.1K context—in / 1M
- Claude Opus 4.5Anthropic · 24 Nov 2025 · 200K context$5.00in / 1M
- GPT-5.1OpenAI · 12 Nov 2025 · 400K context$1.25in / 1M
- ERNIE-4.5-VL-28B-A3B-ThinkingBaidu · 11 Nov 2025 · 131.1K context—in / 1M
- Keye-VL-671B-A37BKuaishou · Nov 2025 · 163.8K context—in / 1M
- Qwen3-VL-2B-ThinkingAlibaba Group · 21 Oct 2025 · 262.1K context—in / 1M
- Qwen3-VL-32B-ThinkingAlibaba Group · 21 Oct 2025 · 262.1K context—in / 1M
- Claude Haiku 4.5Anthropic · 15 Oct 2025 · 200K context$1.00in / 1M
- Qwen3-VL-4B-ThinkingAlibaba Group · 15 Oct 2025 · 262.1K context—in / 1M
- Qwen3-VL-8B-ThinkingAlibaba Group · 15 Oct 2025 · 262.1K context—in / 1M
- Qwen3-VL-FlashAlibaba Group · 14 Oct 2025 · 262.1K context$0.05in / 1M
- Qwen3-VL-30B-A3B-ThinkingAlibaba Group · 3 Oct 2025 · 262.1K context—in / 1M
- Claude Sonnet 4.5Anthropic · 29 Sep 2025 · 200K context$3.00in / 1M
- Qwen3-VL-235B-A22B-ThinkingAlibaba Group · 23 Sep 2025 · 262.1K context—in / 1M
- Qwen3-VL-PlusAlibaba Group · 23 Sep 2025 · 262.1K context$0.20in / 1M
- Qwen3-Omni-30B-A3B-ThinkingAlibaba Group · 22 Sep 2025 · — context—in / 1M
- Hunyuan T1 VisionTencent · 16 Sep 2025 · 28.7K context—in / 1M
- Qwen3-Omni-FlashAlibaba Group · 15 Sep 2025 · 65.5K context—in / 1M
- Qianfan-VL-3BBaidu · Sep 2025 · 32.8K context—in / 1M
- Qianfan-VL-70BBaidu · Sep 2025 · 32.8K context—in / 1M
- Qianfan-VL-8BBaidu · Sep 2025 · 32.8K context—in / 1M
- GLM-4.5VZ.ai (Zhipu AI) · 11 Aug 2025 · 65.5K context$0.60in / 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
- Intern-S1-miniShanghai AI Laboratory · Aug 2025 · 65.5K context—in / 1M
- InternVL3.5-14BShanghai AI Laboratory · Aug 2025 · 41K context—in / 1M
- InternVL3.5-1BShanghai AI Laboratory · Aug 2025 · 41K context—in / 1M
- InternVL3.5-241B-A28BShanghai AI Laboratory · Aug 2025 · 41K context—in / 1M
- InternVL3.5-2BShanghai AI Laboratory · Aug 2025 · 41K context—in / 1M