Calibration
OSWorld 2.0 → CyberGym
CyberGym is estimated from OSWorld 2.0 with a linear curve fitted on 7 models measured on both: y = 0.3022·x + 0.6560, R² = 0.48, cross-validated error 8.4 pp. It is used for 0 estimates.
CyberGym is estimated from OSWorld 2.0 with a linear curve fitted on 7 models measured on both: y = 0.3022·x + 0.6560, R² = 0.48, cross-validated error 8.4 pp. It is used for 0 estimates.