Calibration

Decision Index 0.3 Language → 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 Language with a Hill curve fitted on 112 models measured on both: y = 0.0441 + (1.2000 − 0.0441)·x^1.74 / (0.83231^1.74 + x^1.74), R² = 0.88, cross-validated error 4.5 pp. It is used for 0 estimates.