Calibration

HealthBench Hard → Artificial Analysis Intelligence Index

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

Artificial Analysis Intelligence Index is estimated from HealthBench Hard with a offset logistic curve fitted on 11 models measured on both: y = 0.2803 + (0.4739 − 0.2803) / (1 + exp(−119.32·(x − 0.2727))), R² = 0.47, cross-validated error 10.4 pp. It is used for 0 estimates.