Calibration

Vibe Code Bench → AA LiveCodeBench

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

AA LiveCodeBench is estimated from Vibe Code Bench with a linear curve fitted on 7 models measured on both: y = 0.2320·x + 0.8241, R² = 0.43, cross-validated error 3.4 pp. It is used for 0 estimates.

Fitted on

Model	Vibe Code Bench	AA LiveCodeBench
Claude Opus 4.5 Thinking	20.6%	87.1%
Gemini 2.5 Pro	0.4%	80.1%
Gemini 3 Pro	14.3%	91.7%
GPT-5.1	24.6%	86.8%
GPT-5 (high)	20.1%	84.6%
Grok 4.1 Fast (Reasoning)	1.2%	82.2%
Grok 4 Fast (Reasoning)	0.0%	83.2%