Calibration

BabyVision → CharXiv

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

CharXiv is estimated from BabyVision with a offset logistic curve fitted on 6 models measured on both: y = 0.8688 + (0.9350 − 0.8688) / (1 + exp(−200.00·(x − 0.7691))), R² = 0.48, cross-validated error 4.7 pp. It is used for 0 estimates.