# CharXiv w/o tools → MMMU-Pro

Calibration · https://benchgap.net/calibration/charxivnotools/current/to/mmmu-pro/current · data retrieved 2026-11-21

MMMU-Pro is estimated from CharXiv w/o tools with a inverse Michaelis–Menten curve fitted on 9 models measured on both: y = 1.79877·(x − 0.2318) / (0.2318 + 2.0000 − x), R² = 0.80, cross-validated error 6.6 pp. It is used for 0 estimates.

## Fitted on

| Model | CharXiv w/o tools | MMMU-Pro |
|---|---|---|
| [dots3-note Preview](https://benchgap.net/model/dots3-note-preview.md) | 83.1% | 79.1% |
| [Inkling](https://benchgap.net/model/inkling.md) | 78.1% | 73.5% |
| [Inkling 2 Mini](https://benchgap.net/model/inkling-2-mini.md) | 80.6% | 74.9% |
| [Inkling 2 Small](https://benchgap.net/model/inkling-2-small.md) | 85.6% | 81.6% |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 77.4% | 74.0% |
| [Kimi K3.1 Pro](https://benchgap.net/model/kimi-3-1-pro.md) | 89.0% | 84.1% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 84.8% | 81.6% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 70.2% | 45.7% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 88.4% | 82.3% |
