Calibration

SimpleVQA → AA-MMMU-Pro

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

AA-MMMU-Pro is estimated from SimpleVQA with a offset logistic curve fitted on 7 models measured on both: y = 0.7460 + (0.7967 − 0.7460) / (1 + exp(−160.90·(x − 0.6042))), R² = 0.53, cross-validated error 3.0 pp. It is used for 1 estimate.

Estimated model	SimpleVQA	AA-MMMU-Pro	Source
dots3-note Preview	72.5%	79.7%	estimated ± 3.0 pp, medium confidence