Calibration

HealthBench Hard → AA-GPQA Diamond

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

AA-GPQA Diamond is estimated from HealthBench Hard with a Hill curve fitted on 8 models measured on both: y = 0.0000 + (0.9278 − 0.0000)·x^6.00 / (0.10068^6.00 + x^6.00), R² = 0.59, cross-validated error 4.5 pp. It is used for 0 estimates.