# MMMU — AI model rankings

Tests the AI on understanding images and text together across many college subjects. Higher is better.

7 tracked models have a published MMMU score. Higher is better. Scores are as published at each model's release.

## Ranking

| Rank | Model | Developer | Score | Released |
| --- | --- | --- | --- | --- |
| 1 | Qwen3.5 | Qwen | 85% | Feb 16 2026 |
| 2 | Qwen3.6 | Qwen | 81.7% | Apr 16 2026 |
| 3 | Gemini 3.0 Pro | Google | 81% | Nov 18 2025 |
| 4 | Muse Spark | Meta | 80.4% | Apr 8 2026 |
| 5 | GPT-5.1 | OpenAI | 76% | Nov 12 2025 |
| 6 | Gemini 2.5 Pro | Google | 68% | Mar 25 2025 |
| 6 | Claude Sonnet 4.5 | Anthropic | 68% | Sep 29 2025 |


---

Canonical page: https://aireleasetracker.com/benchmark/mmmu
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Benchmark scores are the figures published by the releasing lab at launch.