Calibration

LABBench2 → AA-HLE

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

AA-HLE is estimated from LABBench2 with a offset logistic curve fitted on 7 models measured on both: y = 0.4065 + (0.5332 − 0.4065) / (1 + exp(−200.00·(x − 0.8184))), R² = 0.75, cross-validated error 4.1 pp. It is used for 0 estimates.