# Video-MME (with subtitle) → MMMU-Pro

Calibration · https://benchgap.net/calibration/1632 · data retrieved 2026-10-29

MMMU-Pro is estimated from Video-MME (with subtitle) with a inverse Michaelis–Menten curve fitted on 12 models measured on both: y = 1.48425·(x − 0.1810) / (0.1810 + 2.0000 − x), R² = 0.88, cross-validated error 4.2 pp. It is used for 0 estimates.

## Fitted on

| Model | Video-MME (with subtitle) | MMMU-Pro |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 77.6% | 70.6% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 88.4% | 81.0% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 86.0% | 79.5% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 87.4% | 78.5% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 69.0% | 45.7% |
| [MiMo-V2.5](https://benchgap.net/model/mimo-v2-5.md) | 87.7% | 77.9% |
| [MiniMax M3](https://benchgap.net/model/minimax-m3.md) | 85.4% | 78.1% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 87.5% | 79.0% |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 87.7% | 75.8% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 86.6% | 75.3% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 88.0% | 79.0% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 90.4% | 82.3% |