List your company

Uncertainty Quantification on MATH

81.7AUROCP(true)
58.61264.60670.676.594Jun 2, 2026

Evaluation results

MethodLinks
P(true)Model=Gemma2026.0681.7
LogTokUModel=Gemma2026.0680.1
Add-S˜Model=Gemma2026.0680.1
GLU-AUModel=Fanar2026.0680.1
GLUModel=Gemma2026.0679.9
GLUModel=Fanar2026.0678.8
RAUQModel=Fanar2026.0677.9
GLU-Sα-SPModel=Qwen2026.0677.2
RAUQModel=Gemma2026.0677.1
GLUModel=Qwen2026.0676.7
P(true)Model=Qwen2026.0675.9
LogProbModel=Fanar2026.0674.6
RAUQModel=Qwen2026.0669.9
LogProbModel=Qwen2026.0668.4
LogProbModel=Gemma2026.0668.3
P(true)Model=Fanar2026.0666.6
LogTokUModel=Fanar2026.0666.4
LogTokUModel=Qwen2026.0659.5