Calibration

Decision Index 0.3 Full Score → Decision Index 0.3 Knowledge

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

Decision Index 0.3 Knowledge is estimated from Decision Index 0.3 Full Score with a inverse Michaelis–Menten curve fitted on 112 models measured on both: y = 0.74436·(x − 0.0000) / (0.0000 + 1.5986 − x), R² = 0.97, cross-validated error 2.5 pp. It is used for 0 estimates.