MMMU-Pro is an AI benchmark used to evaluate model capabilities. Review its overview, metrics, official resources, and model leaderboard results on DataLearnerAI.
Browse the latest scores, model modes, release dates, and parameter sizes for MMMU-Pro.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Kimi K3 Thinking Level · MaxTools | 83.40 | 2026-07-16 | 2800B | Conditional | |
 Seed2.1 Pro Thinking EnabledTools | 82.70 | 2026-06-23 | Unknown | Closed | |
Seed2.1 Pro Thinking Enabled | 81.60 | 2026-06-23 | Unknown | Closed | |
4 | Kimi K3 Thinking Level · Max | 81.60 | 2026-07-16 | 2800B | Conditional |
5 |  Muse Glimmer-30B Thinking Level · High | 74.00 | 2026-08-10 | 29.6B | Free Commercial |
6 |  Gemma 4 E4B Thinking Enabled | 52.60 | 2026-04-02 | 8B | Free Commercial |
7 | Gemma 4 E2B Thinking Enabled | 44.20 | 2026-04-02 | 5.1B | Free Commercial |
