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
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 3.1 Pro | 80.5 | 2026-02-19 | evidence | |
| Gemma 4 (31B) | 76.9 | 2026-03-11 | evidence | |
| Kimi K3 | Moonshot AI | 83.4 | 2026-06-13 | evidence |
| Kimi K3 | Moonshot AI | 81.6 | 2026-06-13 | evidence |
| Qwen3.5-397B-A17B | Qwen | 79.0 | 2026-02-16 | evidence |
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.