Calibration

WideResearch → BrowseComp

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

BrowseComp is estimated from WideResearch with a offset logistic curve fitted on 9 models measured on both: y = 0.5941 + (1.2000 − 0.5941) / (1 + exp(−25.08·(x − 0.8158))), R² = 0.88, cross-validated error 7.2 pp. It is used for 0 estimates.