Calibration

AA-GPQA Diamond → Artificial Analysis Intelligence Index

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

Artificial Analysis Intelligence Index is estimated from AA-GPQA Diamond with a offset logistic curve fitted on 181 models measured on both: y = 0.0807 + (1.2000 − 0.0807) / (1 + exp(−13.13·(x − 0.9950))), R² = 0.86, cross-validated error 4.3 pp. It is used for 0 estimates.