Calibration

We-Math → V*

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap
License: https://creativecommons.org/licenses/by-nc/4.0/

V* is estimated from We-Math with a Michaelis–Menten curve fitted on 5 models measured on both: y = 2.0000·x / (1.10967 + x), R² = 0.38, cross-validated error 10.9 pp. It is used for 0 estimates.

Fitted on

Model	We-Math	V*
Claude Opus 4.5	70.0%	67.0%
Gemini 3 Pro	86.9%	88.0%
GPT-5.2	79.0%	75.9%
LFM3-VL-2B	68.6%	86.4%
Qwen3.5 397B	87.9%	95.8%