Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
LLM Routing on MMLU Pro STEM (Out-of-Domain)
Loading...
59.2
LPM
ProbeDirichlet
55.4352
56.4126
57.39
58.3674
Feb 12, 2026
LPM
MPM
HCR
Updated 4d ago
Evaluation Results
Method
Method
Links
LPM
MPM
HCR
ProbeDirichlet
Signal Modality=Hidden...
2026.02
59.2
71.06
15.75
SemanticEntropy
Signal Modality=Verbos...
2026.02
57.15
69.64
16
SelfAsk
Signal Modality=Verbos...
2026.02
57.01
69.47
13.64
EmbeddingMLP
Signal Modality=Embedd...
2026.02
56.78
69.29
11.42
ConfidenceMargin
Signal Modality=Logit-...
2026.02
56.64
69.47
12.5
MaxLogits
Signal Modality=Logit-...
2026.02
56.07
68.43
10.17
Entropy
Signal Modality=Logit-...
2026.02
55.58
68.79
8.83
Feedback
Search any
task
Search any
task