Calibration

Decision Index 0.3 Tools → 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 Tools with a offset logistic curve fitted on 112 models measured on both: y = 0.0000 + (0.6650 − 0.0000) / (1 + exp(−5.81·(x − 0.4806))), R² = 0.95, cross-validated error 4.4 pp. It is used for 0 estimates.