Calibration

DeepSearchQA → ResearchClawBench

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

ResearchClawBench is estimated from DeepSearchQA with a Michaelis–Menten curve fitted on 6 models measured on both: y = 2.0000·x / (8.62906 + x), R² = 0.41, cross-validated error 2.9 pp. It is used for 0 estimates.