List your company

Ranking on MMLU

0.94CorrelationBayesian
0.85160.874550.89750.92045May 28, 2025

Evaluation results

MethodLinks
Bayesian2025.050.94100
Bradley-Terry2025.050.88647.4
Bootstrap2025.050.88447.4
Simple Average2025.050.88421.1
Single Judge2025.050.85521.1