Google Gemini 3 Deep Think - MMMU-Pro: leaderboard
The "MMMU-Pro" subtask of Google Gemini 3 Deep Think. A benchmark result reported for Google Gemini 3 Deep Think, as self-reported by the model developer.
Metric: Score (%). Source: storage.googleapis.com. Saturation forecast: Around January 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Deep Think | 81.5 | #27 |
| 2 | Gemini 3 Pro (Preview) | 81 | #66 |
| 3 | GPT-5.2 (xHigh) | 79.5 | #110 (GPT-5.2) |
| 4 | Claude Opus 4.6 (Thinking) | 73.9 | #63 (Claude Opus 4.6) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=google-gemini-3-deep-think-mmmu-pro · How It Works · Data refreshed daily, snapshot 2026-10-20.