List your company

Uncertainty Calibration on MATH 500

0.861AUROCET-PE
0.545880.627690.70950.79131Jan 2, 2026

Evaluation results

MethodLinks
ET-PEBackbone=Qwen2.5-14B-Instruct2026.010.861
PEBackbone=Qwen2.5-14B-Instruct2026.010.859
LSBackbone=Qwen2.5-14B-Instruct2026.010.852
ET-PEBackbone=Qwen2.5-7B-Instruct2026.010.84
PEBackbone=Qwen2.5-7B-Instruct2026.010.806
ET-PEBackbone=Qwen2.5-32B-Instruct2026.010.751
PEBackbone=Qwen2.5-32B-Instruct2026.010.751
LSBackbone=Qwen2.5-32B-Instruct2026.010.751
p(True)Backbone=Qwen2.5-7B-Instruct2026.010.736
LSBackbone=Qwen2.5-7B-Instruct2026.010.704
p(True)Backbone=Qwen2.5-32B-Instruct2026.010.694
LN-PEBackbone=Qwen2.5-14B-Instruct2026.010.693
SEBackbone=Qwen2.5-14B-Instruct2026.010.661
p(True)Backbone=Qwen2.5-14B-Instruct2026.010.657
LN-PEBackbone=Qwen2.5-7B-Instruct2026.010.606
LN-PEBackbone=Qwen2.5-32B-Instruct2026.010.599
SEBackbone=Qwen2.5-32B-Instruct2026.010.578
SEBackbone=Qwen2.5-7B-Instruct2026.010.558