Calibration
AA-GPQA Diamond → HLE w/o tools
HLE w/o tools is estimated from AA-GPQA Diamond with a linear curve fitted on 25 models measured on both: y = 2.2130·x + -1.5946, R² = 0.73, cross-validated error 7.8 pp. It is used for 0 estimates.
HLE w/o tools is estimated from AA-GPQA Diamond with a linear curve fitted on 25 models measured on both: y = 2.2130·x + -1.5946, R² = 0.73, cross-validated error 7.8 pp. It is used for 0 estimates.