List your company

Uncertainty Quantification on NQ

85.1AUROCClustered Self-Assessment
59.93266.4667379.534Jun 2, 2026

Evaluation results

MethodLinks
Clustered Self-AssessmentModel=Qwen3-14B, Number of additional samples=22026.0685.1
Clustered Self-AssessmentModel=Qwen2.5-32B, Number of additional samples=22026.0684
Clustered Self-AssessmentModel=Qwen2.5-7B, Number of additional samples=22026.0683.9
Clustered Self-AssessmentModel=Gemma-3-12B, Number of additional samples=22026.0683.7
Clustered Self-AssessmentModel=Qwen3-30B-A3B, Number of additional samples=22026.0683.6
Clustered Self-AssessmentModel=Qwen2.5-14B, Number of additional samples=22026.0683.3
Clustered Self-AssessmentModel=Gemma-3-27B, Number of additional samples=22026.0682.3
P(True)Model=Qwen3-14B, Number of additional samples=22026.0679.9
DegModel=Gemma-3-12B, Number of additional samples=22026.0679
P(True)Model=Qwen2.5-32B, Number of additional samples=22026.0678.5
P(True)Model=Qwen3-30B-A3B, Number of additional samples=22026.0678.3
EigVModel=Qwen2.5-7B, Number of additional samples=22026.0678.1
EigVModel=Qwen3-14B, Number of additional samples=22026.0678
DegModel=Gemma-3-27B, Number of additional samples=22026.0677.7
ProbabilityModel=Qwen2.5-7B, Number of additional samples=22026.0677.6
sentenceSARModel=Qwen2.5-7B, Number of additional samples=22026.0677.6
SARModel=Qwen2.5-7B, Number of additional samples=22026.0677.6
ProbabilityModel=Qwen3-14B, Number of additional samples=22026.0677.4
Predictive EntropyModel=Qwen2.5-7B, Number of additional samples=22026.0677
SARModel=Qwen3-14B, Number of additional samples=22026.0677
sentenceSARModel=Qwen3-14B, Number of additional samples=22026.0676.8
EigVModel=Qwen2.5-32B, Number of additional samples=22026.0676.8
SARModel=Gemma-3-12B, Number of additional samples=22026.0676.5
ProbabilityModel=Qwen2.5-32B, Number of additional samples=22026.0676.3
DegModel=Qwen3-14B, Number of additional samples=22026.0676.3
Predictive EntropyModel=Qwen3-14B, Number of additional samples=22026.0676.2
EigVModel=Qwen3-30B-A3B, Number of additional samples=22026.0676
sentenceSARModel=Qwen2.5-32B, Number of additional samples=22026.0675.9
EigVModel=Gemma-3-12B, Number of additional samples=22026.0675.9
DegModel=Qwen2.5-7B, Number of additional samples=22026.0675.8
ProbabilityModel=Gemma-3-27B, Number of additional samples=22026.0675.5
SARModel=Qwen2.5-32B, Number of additional samples=22026.0675.5
tokenSARModel=Gemma-3-12B, Number of additional samples=22026.0675.4
SARModel=Qwen3-30B-A3B, Number of additional samples=22026.0675.4
Predictive EntropyModel=Qwen2.5-32B, Number of additional samples=22026.0675.3
Semantic EntropyModel=Qwen2.5-7B, Number of additional samples=22026.0675.3
EigVModel=Qwen2.5-14B, Number of additional samples=22026.0675.3
LN EntropyModel=Qwen2.5-7B, Number of additional samples=22026.0675.1
tokenSARModel=Gemma-3-27B, Number of additional samples=22026.0675
Semantic EntropyModel=Qwen3-14B, Number of additional samples=22026.0675
EigVModel=Gemma-3-27B, Number of additional samples=22026.0675
PerplexityModel=Gemma-3-27B, Number of additional samples=22026.0674.9
PerplexityModel=Qwen2.5-7B, Number of additional samples=22026.0674.8
ProbabilityModel=Qwen3-30B-A3B, Number of additional samples=22026.0674.8
DegModel=Qwen2.5-32B, Number of additional samples=22026.0674.8
ProbabilityModel=Qwen2.5-14B, Number of additional samples=22026.0674.7
sentenceSARModel=Qwen2.5-14B, Number of additional samples=22026.0674.7
sentenceSARModel=Qwen3-30B-A3B, Number of additional samples=22026.0674.7
PerplexityModel=Gemma-3-12B, Number of additional samples=22026.0674.5
SARModel=Qwen2.5-14B, Number of additional samples=22026.0674.5
LN EntropyModel=Qwen3-14B, Number of additional samples=22026.0674.4
Predictive EntropyModel=Qwen2.5-14B, Number of additional samples=22026.0674.2
Predictive EntropyModel=Qwen3-30B-A3B, Number of additional samples=22026.0674.2
PerplexityModel=Qwen3-14B, Number of additional samples=22026.0673.7
DegModel=Qwen3-30B-A3B, Number of additional samples=22026.0673.7
Semantic EntropyModel=Qwen2.5-32B, Number of additional samples=22026.0673.5
LN EntropyModel=Qwen3-30B-A3B, Number of additional samples=22026.0673.4
DegModel=Qwen2.5-14B, Number of additional samples=22026.0673.3
tokenSARModel=Qwen2.5-7B, Number of additional samples=22026.0673.2
sentenceSARModel=Gemma-3-12B, Number of additional samples=22026.0673.2
P(True)Model=Qwen2.5-14B, Number of additional samples=22026.0673.1
LN EntropyModel=Qwen2.5-32B, Number of additional samples=22026.0673
PerplexityModel=Qwen3-30B-A3B, Number of additional samples=22026.0672.9
ProbabilityModel=Gemma-3-12B, Number of additional samples=22026.0672.9
P(True)Model=Qwen2.5-7B, Number of additional samples=22026.0672.9
SARModel=Gemma-3-27B, Number of additional samples=22026.0672.9
PerplexityModel=Qwen2.5-32B, Number of additional samples=22026.0672.8
tokenSARModel=Qwen3-14B, Number of additional samples=22026.0672.5
Semantic EntropyModel=Gemma-3-27B, Number of additional samples=22026.0672.5
Semantic EntropyModel=Qwen3-30B-A3B, Number of additional samples=22026.0672.4
Predictive EntropyModel=Gemma-3-12B, Number of additional samples=22026.0672.2
sentenceSARModel=Gemma-3-27B, Number of additional samples=22026.0672.1
LN EntropyModel=Gemma-3-12B, Number of additional samples=22026.0672
Predictive EntropyModel=Gemma-3-27B, Number of additional samples=22026.0671.9
Semantic EntropyModel=Qwen2.5-14B, Number of additional samples=22026.0671.9
LN EntropyModel=Qwen2.5-14B, Number of additional samples=22026.0671.6
tokenSARModel=Qwen2.5-32B, Number of additional samples=22026.0671.4
tokenSARModel=Qwen3-30B-A3B, Number of additional samples=22026.0671.4
EccModel=Qwen3-14B, Number of additional samples=22026.0671.4
Eigen ScoreModel=Qwen2.5-7B, Number of additional samples=22026.0671.3
Semantic EntropyModel=Gemma-3-12B, Number of additional samples=22026.0670.7
EccModel=Qwen2.5-7B, Number of additional samples=22026.0670.7
PerplexityModel=Qwen2.5-14B, Number of additional samples=22026.0670.6
EccModel=Qwen2.5-32B, Number of additional samples=22026.0670.2
tokenSARModel=Qwen2.5-14B, Number of additional samples=22026.0670.1
Eigen ScoreModel=Qwen3-14B, Number of additional samples=22026.0669.9
EccModel=Qwen2.5-14B, Number of additional samples=22026.0669.7
LN EntropyModel=Gemma-3-27B, Number of additional samples=22026.0669.3
EccModel=Qwen3-30B-A3B, Number of additional samples=22026.0669.2
Eigen ScoreModel=Qwen2.5-32B, Number of additional samples=22026.0669.1
Eigen ScoreModel=Qwen2.5-14B, Number of additional samples=22026.0667.8
EccModel=Gemma-3-27B, Number of additional samples=22026.0667
Eigen ScoreModel=Qwen3-30B-A3B, Number of additional samples=22026.0666.7
EccModel=Gemma-3-12B, Number of additional samples=22026.0666.5
P(True)Model=Gemma-3-27B, Number of additional samples=22026.0665.9
Eigen ScoreModel=Gemma-3-27B, Number of additional samples=22026.0664.1
Eigen ScoreModel=Gemma-3-12B, Number of additional samples=22026.0663.1
P(True)Model=Gemma-3-12B, Number of additional samples=22026.0660.9