Calibration

Decision Index 0.3 Language → Decision Index 0.3 Full Score

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

Decision Index 0.3 Full Score is estimated from Decision Index 0.3 Language with a linear curve fitted on 112 models measured on both: y = 0.9633·x + -0.0031, R² = 0.96, cross-validated error 3.8 pp. It is used for 0 estimates.