# VideoMMMU → We-Math

Calibration · https://benchgap.net/calibration/1649 · data retrieved 2026-10-29

We-Math is estimated from VideoMMMU with a Michaelis–Menten + offset curve fitted on 6 models measured on both: y = 0.4539 + 2.0000·x / (3.85891 + x), R² = 0.43, cross-validated error 8.7 pp. It is used for 0 estimates.

## Fitted on

| Model | VideoMMMU | We-Math |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 84.4% | 70.0% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 87.6% | 86.9% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 85.9% | 79.0% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 86.6% | 84.7% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 49.6% | 68.6% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 84.7% | 87.9% |