Calibration

V* → ERQA

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

ERQA is estimated from V* with a Michaelis–Menten curve fitted on 6 models measured on both: y = 2.0000·x / (2.00140 + x), R² = 0.42, cross-validated error 8.5 pp. It is used for 0 estimates.

Fitted on

Model	V*	ERQA
Claude Opus 4.5	67.0%	46.8%
Gemini 3 Pro	88.0%	70.5%
GPT-5.2	75.9%	59.8%
LFM3-VL-2B	86.4%	48.2%
Qwen3.5 397B	95.8%	67.5%
Qwen3.6-27B	94.7%	62.5%