# VideoMMMU → MMMU-Pro

Calibration · https://benchgap.net/calibration/1645 · data retrieved 2026-10-29

MMMU-Pro is estimated from VideoMMMU with a Michaelis–Menten curve fitted on 13 models measured on both: y = 2.0000·x / (1.35131 + x), R² = 0.87, cross-validated error 3.5 pp. It is used for 0 estimates.

## Fitted on

| Model | VideoMMMU | MMMU-Pro |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 84.4% | 70.6% |
| [dots3-note Preview](https://benchgap.net/model/dots3-note-preview.md) | 86.8% | 79.1% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 87.6% | 81.0% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 85.9% | 79.5% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 86.6% | 78.5% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 49.6% | 45.7% |
| [MiniMax M3](https://benchgap.net/model/minimax-m3.md) | 84.6% | 78.1% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 84.7% | 79.0% |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 84.4% | 75.8% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 83.7% | 75.3% |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 84.0% | 78.8% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 85.4% | 79.0% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 88.7% | 82.3% |