Calibration

Decision Index 0.3 Language → Decision Index 0.3 Retrieval

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

Decision Index 0.3 Retrieval is estimated from Decision Index 0.3 Language with a offset logistic curve fitted on 112 models measured on both: y = 0.0000 + (1.0570 − 0.0000) / (1 + exp(−3.70·(x − 0.5214))), R² = 0.73, cross-validated error 9.0 pp. It is used for 0 estimates.