Calibration

MathVision w/ Python → CharXiv w/o tools

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

CharXiv w/o tools is estimated from MathVision w/ Python with a Michaelis–Menten + offset curve fitted on 5 models measured on both: y = 0.0000 + 2.0000·x / (1.30412 + x), R² = 0.33, cross-validated error 1.9 pp. It is used for 0 estimates.