List your company

Uncertainty Calibration on GPQA diamond

0.696AUROCET-PE
0.450560.514280.5780.64172Jan 2, 2026

Evaluation results

MethodLinks
ET-PEBackbone=Qwen2.5-14B-Instruct2026.010.696
ET-PEBackbone=Qwen2.5-32B-Instruct2026.010.684
LSBackbone=Qwen2.5-32B-Instruct2026.010.682
PEBackbone=Qwen2.5-14B-Instruct2026.010.671
PEBackbone=Qwen2.5-32B-Instruct2026.010.649
ET-PEBackbone=Qwen2.5-7B-Instruct2026.010.638
p(True)Backbone=Qwen2.5-7B-Instruct2026.010.638
LSBackbone=Qwen2.5-7B-Instruct2026.010.631
p(True)Backbone=Qwen2.5-32B-Instruct2026.010.627
p(True)Backbone=Qwen2.5-14B-Instruct2026.010.626
PEBackbone=Qwen2.5-7B-Instruct2026.010.621
LSBackbone=Qwen2.5-14B-Instruct2026.010.607
SEBackbone=Qwen2.5-32B-Instruct2026.010.604
LN-PEBackbone=Qwen2.5-32B-Instruct2026.010.583
SEBackbone=Qwen2.5-14B-Instruct2026.010.582
LN-PEBackbone=Qwen2.5-14B-Instruct2026.010.578
SEBackbone=Qwen2.5-7B-Instruct2026.010.484
LN-PEBackbone=Qwen2.5-7B-Instruct2026.010.46