Calibration

Decision Index 0.3 Retrieval → Decision Index 0.3 Arts

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

Decision Index 0.3 Arts is estimated from Decision Index 0.3 Retrieval with a Hill curve fitted on 112 models measured on both: y = 0.0848 + (1.2000 − 0.0848)·x^2.54 / (0.80059^2.54 + x^2.54), R² = 0.75, cross-validated error 7.4 pp. It is used for 0 estimates.