List your company

Uncertainty Calibration on TQA

0.0721Brier ScoreClustered Self-Assessment
0.0653760.1107630.156150.201537Jun 2, 2026

Evaluation results

MethodLinks
Clustered Self-AssessmentBackbone=Gemma-3-27B2026.060.0721
Clustered Self-AssessmentBackbone=Qwen2.5-32B2026.060.0843
Clustered Self-AssessmentBackbone=Qwen3-30B-A3B2026.060.0894
Clustered Self-AssessmentBackbone=Qwen2.5-14B2026.060.0917
Clustered Self-AssessmentBackbone=Qwen3-14B2026.060.0921
NSEBackbone=Gemma-3-27B2026.060.0937
Clustered Self-AssessmentBackbone=Gemma-3-12B2026.060.0943
P(True)Backbone=Qwen2.5-32B2026.060.1172
Clustered Self-AssessmentBackbone=Qwen2.5-7B2026.060.1183
NSEBackbone=Qwen2.5-32B2026.060.12
NSEBackbone=Qwen3-14B2026.060.1283
NSEBackbone=Qwen3-30B-A3B2026.060.1289
P(True)Backbone=Qwen3-14B2026.060.1315
NSEBackbone=Qwen2.5-14B2026.060.1342
P(True)Backbone=Qwen3-30B-A3B2026.060.1398
P(True)Backbone=Qwen2.5-14B2026.060.14
NSEBackbone=Gemma-3-12B2026.060.1421
NSEBackbone=Qwen2.5-7B2026.060.158
ProbabilityBackbone=Qwen2.5-7B2026.060.1674
P(True)Backbone=Qwen2.5-7B2026.060.1708
P(True)Backbone=Gemma-3-27B2026.060.1758
ProbabilityBackbone=Qwen3-14B2026.060.1807
ProbabilityBackbone=Qwen3-30B-A3B2026.060.1917
ProbabilityBackbone=Gemma-3-27B2026.060.1975
ProbabilityBackbone=Qwen2.5-14B2026.060.2001
P(True)Backbone=Gemma-3-12B2026.060.2147
ProbabilityBackbone=Qwen2.5-32B2026.060.2267
ProbabilityBackbone=Gemma-3-12B2026.060.2402