Calibration
ScreenSpot Pro → AA-MMMU-Pro
AA-MMMU-Pro is estimated from ScreenSpot Pro with a offset logistic curve fitted on 12 models measured on both: y = 0.5898 + (0.7960 − 0.5898) / (1 + exp(−200.00·(x − 0.6734))), R² = 0.71, cross-validated error 9.4 pp. It is used for 4 estimates.
| Estimated model | ScreenSpot Pro | AA-MMMU-Pro | Source |
|---|---|---|---|
| Holo2-235B-A22B | 70.6% | 79.6% | estimated ± 9.4 pp, medium confidence |
| Holo2-30B-A3B | 66.1% | 60.6% | estimated ± 9.4 pp, medium confidence |
| Holo2-4B | 57.2% | 59.0% | estimated ± 9.4 pp, medium confidence |
| Holo2-8B | 58.9% | 59.0% | estimated ± 9.4 pp, medium confidence |