Calibration

VulcanBench v3 → FrontierCode 1.1 Extended

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

FrontierCode 1.1 Extended is estimated from VulcanBench v3 with a offset logistic curve fitted on 5 models measured on both: y = 0.5454 + (0.6584 − 0.5454) / (1 + exp(−200.00·(x − 0.8698))), R² = 0.40, cross-validated error 3.4 pp. It is used for 0 estimates.