Benchmark

MMMU-Pro

Harder vision-required subset of MMMU. Input image ordering changes the result, so the protocol has to travel with the number.

Released
2024-09-04
Categories
multimodal
Openness
unknown
Source
model_reports
Reported scores
5

Reported scores

model_reports

ModelOrganizationReported valueReportedEvidence
Gemini 3.1 ProGoogle80.52026-02-19evidence
Gemma 4 (31B)Google76.92026-03-11evidence
Kimi K3Moonshot AI83.42026-06-13evidence
Kimi K3Moonshot AI81.62026-06-13evidence
Qwen3.5-397B-A17BQwen79.02026-02-16evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.