Calibration

Vals GPQA Diamond → HealthBench Professional

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

HealthBench Professional is estimated from Vals GPQA Diamond with a Michaelis–Menten + offset curve fitted on 5 models measured on both: y = 0.0000 + 2.0000·x / (2.23116 + x), R² = 0.37, cross-validated error 1.7 pp. It is used for 1 estimate.

Estimated model	Vals GPQA Diamond	HealthBench Professional	Source
MiMo-V2-Flash	59.3%	42.0%	estimated ± 1.7 pp, low confidence