Calibration
ScreenSpot Pro → VideoMMMU
VideoMMMU is estimated from ScreenSpot Pro with a Hill curve fitted on 6 models measured on both: y = 0.8391 + (1.2000 − 0.8391)·x^6.00 / (1.18486^6.00 + x^6.00), R² = 0.59, cross-validated error 1.7 pp. It is used for 5 estimates.
| Estimated model | ScreenSpot Pro | VideoMMMU | Source |
|---|---|---|---|
| GPT-6 Astra | 92.7% | 90.6% | estimated ± 1.7 pp, low confidence |
| Holo2-235B-A22B | 70.6% | 85.5% | estimated ± 1.7 pp, medium confidence |
| Holo2-30B-A3B | 66.1% | 85.0% | estimated ± 1.7 pp, medium confidence |
| Holo2-4B | 57.2% | 84.4% | estimated ± 1.7 pp, medium confidence |
| Holo2-8B | 58.9% | 84.4% | estimated ± 1.7 pp, medium confidence |