Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
LLM Routing on Big Math In-Domain
Loading...
0.6618
AUROC
ProbeDirichlet
0.464408
0.515654
0.5669
0.618146
Feb 12, 2026
AUROC
Updated 4d ago
Evaluation Results
Method
Method
Links
AUROC
ProbeDirichlet
signal_modality=Hidden...
2026.02
0.6618
ConfidenceMargin
signal_modality=Logit-...
2026.02
0.5618
EmbeddingMLP
signal_modality=Embedd...
2026.02
0.5618
SemanticEntropy
signal_modality=Verbos...
2026.02
0.5581
Entropy
signal_modality=Logit-...
2026.02
0.5141
MaxLogits
signal_modality=Logit-...
2026.02
0.4739
SelfAsk
signal_modality=Verbos...
2026.02
0.472
Feedback
Search any
task
Search any
task