Calibration
CharXiv w/o tools → AA-MMMU-Pro
AA-MMMU-Pro is estimated from CharXiv w/o tools with a Michaelis–Menten curve fitted on 9 models measured on both: y = 2.0000·x / (1.25462 + x), R² = 0.52, cross-validated error 3.2 pp. It is used for 1 estimate.
| Estimated model | CharXiv w/o tools | AA-MMMU-Pro | Source |
|---|---|---|---|
| Claude Mythos 5 | 88.9% | 82.9% | estimated ± 3.2 pp, medium confidence |