Claude 3 Opus, Claude 3 Sonnet, Claude 3 Haiku
Anthropic
rich detail 18 method fields published
Evaluation
MMMU
Multimodal understanding
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.
o3, o4-mini
OpenAI
rich detail 10 method fields published
See how this test was run
Claude Opus 4, Claude Sonnet 4
Anthropic
rich detail 18 method fields published
See how this test was run
GPT-5
OpenAI
rich detail 8 method fields published