List your company

Uncertainty Quantification on MATH (PRR)

70PRRGLU-Sα-SP
19.66432.73245.858.868Jun 2, 2026

Evaluation results

MethodLinks
GLU-Sα-SPModel=Gemma2026.0670
GLUModel=Gemma2026.0669.9
LogTokUModel=Gemma2026.0669.3
GLU-AUModel=Fanar2026.0664.8
RAUQModel=Gemma2026.0663.9
P(true)Model=Gemma2026.0663.6
GLUModel=Fanar2026.0662.7
RAUQModel=Fanar2026.0662.4
P(true)Model=Qwen2026.0657.4
GLU-Sα-SPModel=Qwen2026.0654.5
GLUModel=Qwen2026.0653.7
LogProbModel=Fanar2026.0652
LogProbModel=Gemma2026.0643.8
RAUQModel=Qwen2026.0642.4
LogProbModel=Qwen2026.0638.1
P(true)Model=Fanar2026.0632.5
LogTokUModel=Fanar2026.0632.4
LogTokUModel=Qwen2026.0621.6