Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
LLM Routing on MMLU Pro Social Sciences (Out-of-Domain)
Loading...
59.2
LPM
SelfAsk
55.0816
56.1508
57.22
58.2892
Feb 12, 2026
LPM
MPM
HCR
Updated 4d ago
Evaluation Results
Method
Method
Links
LPM
MPM
HCR
SelfAsk
Signal Modality=Verbos...
2026.02
59.2
69.66
11
ProbeDirichlet
Signal Modality=Hidden...
2026.02
59.12
69.16
14.83
ConfidenceMargin
Signal Modality=Logit-...
2026.02
58.81
68.36
11.68
SemanticEntropy
Signal Modality=Verbos...
2026.02
57.4
67.71
13.33
Entropy
Signal Modality=Logit-...
2026.02
57.1
67.69
10.5
EmbeddingMLP
Signal Modality=Embedd...
2026.02
56.38
67.15
9.67
MaxLogits
Signal Modality=Logit-...
2026.02
55.24
66.13
7.5
Feedback
Search any
task
Search any
task