# VideoMMMU → Video-MME (w/o subtitle)

Calibration · https://benchgap.net/calibration/1647 · data retrieved 2026-10-29

Video-MME (w/o subtitle) is estimated from VideoMMMU with a Michaelis–Menten + offset curve fitted on 7 models measured on both: y = 0.1866 + 2.0000·x / (1.75852 + x), R² = 0.96, cross-validated error 2.3 pp. It is used for 0 estimates.

## Fitted on

| Model | VideoMMMU | Video-MME (w/o subtitle) |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 84.4% | 81.4% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 87.6% | 87.7% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 85.9% | 85.8% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 86.6% | 83.2% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 49.6% | 62.8% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 84.7% | 83.7% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 83.7% | 82.5% |