Calibration

MMLU-Pro → Artificial Analysis Intelligence Index

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

Artificial Analysis Intelligence Index is estimated from MMLU-Pro with a Hill curve fitted on 36 models measured on both: y = 0.0116 + (1.2000 − 0.0116)·x^6.00 / (1.10051^6.00 + x^6.00), R² = 0.47, cross-validated error 7.0 pp. It is used for 0 estimates.