List your company

Uncertainty Quantification on NQ 4 additional samples (test)

85.3AUROCClustered Self-Assessment
59.92466.51273.179.688Jun 2, 2026

Evaluation results

MethodLinks
Clustered Self-AssessmentModel=Qwen3-14B2026.0685.3
Clustered Self-AssessmentModel=Qwen2.5-7B2026.0684.6
Clustered Self-AssessmentModel=Qwen2.5-32B2026.0684.3
Clustered Self-AssessmentModel=Gemma-3-12B2026.0684.2
Clustered Self-AssessmentModel=Qwen3-30B-A3B2026.0683.9
Clustered Self-AssessmentModel=Qwen2.5-14B2026.0683.6
Clustered Self-AssessmentModel=Gemma-3-27B2026.0682.4
EigVModel=Qwen2.5-7B2026.0680.8
EigVModel=Qwen3-14B2026.0680.2
P(True)Model=Qwen3-14B2026.0679.9
DegModel=Gemma-3-12B2026.0679.9
Semantic EntropyModel=Qwen3-14B2026.0679.4
EigVModel=Qwen2.5-32B2026.0679.1
Semantic EntropyModel=Qwen2.5-7B2026.0679
EigVModel=Qwen3-30B-A3B2026.0678.6
P(True)Model=Qwen2.5-32B2026.0678.5
P(True)Model=Qwen3-30B-A3B2026.0678.3
DegModel=Gemma-3-27B2026.0678.3
SARModel=Qwen2.5-7B2026.0678.1
Semantic EntropyModel=Qwen2.5-32B2026.0677.9
SARModel=Qwen3-14B2026.0677.8
DegModel=Qwen2.5-7B2026.0677.8
sentenceSARModel=Qwen2.5-7B2026.0677.7
DegModel=Qwen3-14B2026.0677.7
ProbabilityModel=Qwen2.5-7B2026.0677.6
EigVModel=Qwen2.5-14B2026.0677.6
ProbabilityModel=Qwen3-14B2026.0677.4
Predictive EntropyModel=Qwen2.5-7B2026.0677
sentenceSARModel=Qwen3-14B2026.0677
Semantic EntropyModel=Qwen3-30B-A3B2026.0676.6
SARModel=Qwen3-30B-A3B2026.0676.5
DegModel=Qwen2.5-32B2026.0676.5
ProbabilityModel=Qwen2.5-32B2026.0676.3
Predictive EntropyModel=Qwen3-14B2026.0676.3
SARModel=Qwen2.5-32B2026.0676.3
EigVModel=Gemma-3-12B2026.0676
sentenceSARModel=Qwen2.5-32B2026.0675.7
SARModel=Qwen2.5-14B2026.0675.6
DegModel=Qwen3-30B-A3B2026.0675.6
ProbabilityModel=Gemma-3-27B2026.0675.5
tokenSARModel=Gemma-3-12B2026.0675.4
Semantic EntropyModel=Qwen2.5-14B2026.0675.4
LN EntropyModel=Qwen2.5-7B2026.0675.3
DegModel=Qwen2.5-14B2026.0675.3
Predictive EntropyModel=Qwen2.5-32B2026.0675
tokenSARModel=Gemma-3-27B2026.0675
sentenceSARModel=Qwen2.5-14B2026.0675
sentenceSARModel=Qwen3-30B-A3B2026.0675
PerplexityModel=Gemma-3-27B2026.0674.9
PerplexityModel=Qwen2.5-7B2026.0674.8
ProbabilityModel=Qwen3-30B-A3B2026.0674.8
ProbabilityModel=Qwen2.5-14B2026.0674.7
LN EntropyModel=Qwen3-14B2026.0674.7
PerplexityModel=Gemma-3-12B2026.0674.5
EigVModel=Gemma-3-27B2026.0674.5
Predictive EntropyModel=Qwen2.5-14B2026.0674.4
SARModel=Gemma-3-12B2026.0674.4
Predictive EntropyModel=Qwen3-30B-A3B2026.0674.3
EccModel=Qwen3-14B2026.0674
PerplexityModel=Qwen3-14B2026.0673.7
Eigen ScoreModel=Qwen2.5-7B2026.0673.7
LN EntropyModel=Qwen3-30B-A3B2026.0673.6
EccModel=Qwen2.5-7B2026.0673.5
LN EntropyModel=Qwen2.5-32B2026.0673.2
tokenSARModel=Qwen2.5-7B2026.0673.2
P(True)Model=Qwen2.5-14B2026.0673.1
Eigen ScoreModel=Qwen3-14B2026.0673
PerplexityModel=Qwen3-30B-A3B2026.0672.9
ProbabilityModel=Gemma-3-12B2026.0672.9
P(True)Model=Qwen2.5-7B2026.0672.9
EccModel=Qwen2.5-32B2026.0672.9
PerplexityModel=Qwen2.5-32B2026.0672.8
tokenSARModel=Qwen3-14B2026.0672.5
Eigen ScoreModel=Qwen2.5-32B2026.0672.2
Semantic EntropyModel=Gemma-3-12B2026.0672.1
EccModel=Qwen2.5-14B2026.0672.1
LN EntropyModel=Qwen2.5-14B2026.0672
sentenceSARModel=Gemma-3-12B2026.0672
Semantic EntropyModel=Gemma-3-27B2026.0671.5
tokenSARModel=Qwen2.5-32B2026.0671.4
tokenSARModel=Qwen3-30B-A3B2026.0671.4
EccModel=Qwen3-30B-A3B2026.0671.4
Predictive EntropyModel=Gemma-3-12B2026.0671.1
Eigen ScoreModel=Qwen2.5-14B2026.0671
sentenceSARModel=Gemma-3-27B2026.0670.7
PerplexityModel=Qwen2.5-14B2026.0670.6
SARModel=Gemma-3-27B2026.0670.6
Predictive EntropyModel=Gemma-3-27B2026.0670.5
EccModel=Gemma-3-27B2026.0670.5
LN EntropyModel=Gemma-3-12B2026.0670.3
Eigen ScoreModel=Qwen3-30B-A3B2026.0670.2
tokenSARModel=Qwen2.5-14B2026.0670.1
EccModel=Gemma-3-12B2026.0669.7
LN EntropyModel=Gemma-3-27B2026.0667.3
P(True)Model=Gemma-3-27B2026.0665.9
Eigen ScoreModel=Gemma-3-12B2026.0664.5
Eigen ScoreModel=Gemma-3-27B2026.0664.5
P(True)Model=Gemma-3-12B2026.0660.9