Calibration

HealthBench Professional (raw) → Artificial Analysis Intelligence Index

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

Artificial Analysis Intelligence Index is estimated from HealthBench Professional (raw) with a Michaelis–Menten curve fitted on 7 models measured on both: y = 2.0000·x / (2.02896 + x), R² = 0.62, cross-validated error 4.6 pp. It is used for 0 estimates.