Moonshot AI Kimi K3 (max)81.6% huggingface.co for Kimi K3 (max) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported July 16, 2026 Model card Moonshot AI Self-reported Record for Kimi K3 on MMMU-Pro No tools 120003 OpenAI GPT-5.6 Luna 78.4% openai.com for GPT-5.6 Luna on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Luna on MMMU-Pro No tools 10009 OpenAI GPT-5.6 Sol 83.0% openai.com for GPT-5.6 Sol on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on MMMU-Pro No tools 10010 OpenAI GPT-5.6 Terra 80.7% openai.com for GPT-5.6 Terra on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Terra on MMMU-Pro No tools 10011 Google (DeepMind) Gemini 3.5 Flash 83.6% deepmind.google for Gemini 3.5 Flash on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Overall (Standard 10 options + Vision) Reported May 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.5 Flash on MMMU-Pro No tools 30006 OpenAI GPT-5.5 (xhigh)81.2% openai.com for GPT-5.5 (xhigh) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported April 23, 2026 Launch post OpenAI Self-reported Record for GPT-5.5 on MMMU-Pro No tools 10008 Moonshot AI Kimi K2.6 (thinking)79.4% huggingface.co for Kimi K2.6 (thinking) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported April 20, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.6 on MMMU-Pro No tools 120002 Alibaba (Tongyi) Qwen3.6-35B-A3B 75.3% huggingface.co for Qwen3.6-35B-A3B on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported April 17, 2026 Model card Qwen Self-reported Qwen Team Record for Qwen3.6-35B-A3B on MMMU-Pro No tools 130005 Meta AI (originally Facebook AI Research) Muse Spark (thinking)80.4% ai.meta.com for Muse Spark (thinking) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Standard (10 options) Reported April 8, 2026 Evaluation methodology Meta Self-reported Record for Muse Spark on MMMU-Pro No tools 80001 Mistral AI Mistral Small 4 (high)60.0% huggingface.co for Mistral Small 4 (high) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported March 16, 2026 Model card Mistral AI Self-reported Record for Mistral Small 4 on MMMU-Pro No tools 90004 Mistral AI Mistral Small 4 (none)46.3% huggingface.co for Mistral Small 4 (none) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported March 16, 2026 Model card Mistral AI Self-reported Record for Mistral Small 4 on MMMU-Pro No tools 90004 OpenAI GPT-5.4 (xhigh)81.2% openai.com for GPT-5.4 (xhigh) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on MMMU-Pro No tools 10007 Google (DeepMind) Gemini 3.1 Pro (High)80.5% deepmind.google for Gemini 3.1 Pro (High) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Overall (Standard 10 options + Vision) Reported February 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.1 Pro on MMMU-Pro No tools 30005 Anthropic Claude Sonnet 4.6 (adaptive thinking, max)74.5% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Overall (Standard 10 options + Vision) Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on MMMU-Pro No tools 20009 Moonshot AI Kimi K2.5 (thinking)78.5% huggingface.co for Kimi K2.5 (thinking) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on MMMU-Pro No tools 120001 Google (DeepMind) Gemini 3 Flash 81.2% blog.google for Gemini 3 Flash on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Overall (Standard 10 options + Vision) Reported December 17, 2025 Launch post Google Self-reported Google DeepMind Record for Gemini 3 Flash on MMMU-Pro No tools 30009 OpenAI GPT-5.2 (xhigh)79.5% openai.com for GPT-5.2 (xhigh) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on MMMU-Pro No tools 10012 Google (DeepMind) Gemini 3 Pro (high)81.0% blog.google for Gemini 3 Pro (high) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Overall (Standard 10 options + Vision) Reported November 18, 2025 Launch post Google Self-reported Google DeepMind Record for Gemini 3 Pro on MMMU-Pro No tools 30008