Calibration
DeepPlanning → QwenClawBench
QwenClawBench is estimated from DeepPlanning with a linear curve fitted on 7 models measured on both: y = 0.1549·x + 0.4994, R² = 0.55, cross-validated error 3.7 pp. It is used for 0 estimates.
QwenClawBench is estimated from DeepPlanning with a linear curve fitted on 7 models measured on both: y = 0.1549·x + 0.4994, R² = 0.55, cross-validated error 3.7 pp. It is used for 0 estimates.