Results

17 results

MMMU-Pro No tools results
ProviderModelScoreSourceRegistry No.
Moonshot AIKimi K3 (max)81.6%Source for Kimi K3 (max) on MMMU-Pro No tools (opens in a new tab)120003
OpenAIGPT-5.6 Luna78.4%Source for GPT-5.6 Luna on MMMU-Pro No tools (opens in a new tab)10009
OpenAIGPT-5.6 Sol83.0%Source for GPT-5.6 Sol on MMMU-Pro No tools (opens in a new tab)10010
OpenAIGPT-5.6 Terra80.7%Source for GPT-5.6 Terra on MMMU-Pro No tools (opens in a new tab)10011
Google (DeepMind)Gemini 3.5 Flash83.6%Source for Gemini 3.5 Flash on MMMU-Pro No tools (opens in a new tab)30006
OpenAIGPT-5.5 (xhigh)81.2%Source for GPT-5.5 (xhigh) on MMMU-Pro No tools (opens in a new tab)10008
Moonshot AIKimi K2.6 (thinking)79.4%Source for Kimi K2.6 (thinking) on MMMU-Pro No tools (opens in a new tab)120002
Alibaba (Tongyi)Qwen3.6-35B-A3B75.3%Source for Qwen3.6-35B-A3B on MMMU-Pro No tools (opens in a new tab)130005
Mistral AIMistral Small 4 (high)60.0%Source for Mistral Small 4 (high) on MMMU-Pro No tools (opens in a new tab)90004
Mistral AIMistral Small 4 (none)46.3%Source for Mistral Small 4 (none) on MMMU-Pro No tools (opens in a new tab)90004
OpenAIGPT-5.4 (xhigh)81.2%Source for GPT-5.4 (xhigh) on MMMU-Pro No tools (opens in a new tab)10007
Google (DeepMind)Gemini 3.1 Pro (High)80.5%Source for Gemini 3.1 Pro (High) on MMMU-Pro No tools (opens in a new tab)30005
AnthropicClaude Sonnet 4.6 (adaptive thinking, max)74.5%Source for Claude Sonnet 4.6 (adaptive thinking, max) on MMMU-Pro No tools (opens in a new tab)20009
Moonshot AIKimi K2.5 (thinking)78.5%Source for Kimi K2.5 (thinking) on MMMU-Pro No tools (opens in a new tab)120001
Google (DeepMind)Gemini 3 Flash81.2%Source for Gemini 3 Flash on MMMU-Pro No tools (opens in a new tab)30009
OpenAIGPT-5.2 (xhigh)79.5%Source for GPT-5.2 (xhigh) on MMMU-Pro No tools (opens in a new tab)10012
Google (DeepMind)Gemini 3 Pro (high)81.0%Source for Gemini 3 Pro (high) on MMMU-Pro No tools (opens in a new tab)30008