MMMU Benchmark: leaderboard
Massive Multi-discipline Multimodal Understanding benchmark. Tests academic visual reasoning across 30 subjects spanning science, engineering, art, and more.
Metric: Validation Score. Source: mmmu-benchmark.github.io. Saturation forecast: Estimated already saturated. 189 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Best Expert | 88.6 | |
| 2 | GPT-5.1 | 85.4 | #135 |
| 3 | GPT-5 (Thinking) | 84.2 | #98 (GPT-5) |
| 4 | Gemini 2.5 Pro (Thinking) | 84 | #152 (Gemini 2.5 Pro) |
| 5 | O3 | 82.9 | #124 |
| 6 | Median Expert | 82.6 | |
| 7 | O4 Mini | 81.6 | #180 |
| 8 | Claude Opus 4.5 | 80.7 | #83 |
| 9 | Gemini 2.5 Flash (Preview 05-20) | 79.7 | #216 |
| 10 | Gemini 2.5 Pro (Preview 05-06) | 79.6 | #147 |
| 11 | Qwen 3 VL 235B A22B | 78.7 | #238 |
| 12 | O1 | 78.2 | #183 |
| 13 | Grok 3 | 78 | #304 |
| 14 | Claude Sonnet 4.5 | 77.8 | #142 |
| 15 | Intern-S1 | 77.7 | #285 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mmmu-benchmark · How It Works · Data refreshed daily, snapshot 2026-10-20.