Calibration

MMMU-Pro → ERQA

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap

ERQA is estimated from MMMU-Pro with a Hill curve fitted on 10 models measured on both: y = 0.0000 + (1.1515 − 0.0000)·x^6.00 / (0.75842^6.00 + x^6.00), R² = 0.57, cross-validated error 6.1 pp. It is used for 2 estimates.

Estimated model	MMMU-Pro	ERQA	Source
Interfaze Beta	71.1%	46.6%	estimated ± 6.1 pp, low confidence
Pareto 26.9	78.0%	62.4%	estimated ± 6.1 pp, medium confidence