# MMMU-Pro (standard and vision mean) — AI model rankings

average across the standard and vision sets

5 tracked models have a published MMMU-Pro (standard and vision mean) score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | GPT-5 | OpenAI | 78.4% | Lab | Aug 7 2025 |
| 2 | GPT-5 mini | OpenAI | 74.1% | Lab | Aug 7 2025 |
| 3 | GPT-5 nano | OpenAI | 62.6% | Lab | Aug 7 2025 |
| 4 | LLaMA 4 Maverick | Meta | 59.6% | Lab | Apr 5 2025 |
| 5 | LLaMA 4 Scout | Meta | 52.2% | Lab | Apr 5 2025 |


---

Canonical page: https://aireleasetracker.com/benchmark/mmmu-pro-standard-vision-mean
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.