Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Query Routing on SQuAD, HellaSwag, and HeadQA (out-of-domain)
Loading...
89
Accuracy
Oracle
33.88
48.19
62.5
76.81
Oct 22, 2025
Accuracy
Cost
Utility
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Cost
Utility
Oracle
Category=Topline, alph...
2025.10
89
0.33
0.72
Largest LLM
Category=Naive Baselin...
2025.10
74
0.9
0.29
DiSRouter (SFT)
Optimization=SFT, alph...
2025.10
74
0.62
0.43
DiSRouter (+ RL)
Optimization=+ RL, alp...
2025.10
69
0.43
0.48
GraphRouter
Category=Router Baseli...
2025.10
64
0.49
0.39
FORC
Category=Router Baseli...
2025.10
63
0.53
0.36
Random
Category=Naive Baselin...
2025.10
59
0.46
0.36
FrugalGPT
Category=Router Baseli...
2025.10
55
0.25
0.42
Automix
Category=Router Baseli...
2025.10
55
0.6
0.25
RouteLLM
Category=Router Baseli...
2025.10
42
0.22
0.31
Smallest LLM
Category=Naive Baselin...
2025.10
36
0.1
0.31
Feedback
Search any
task
Search any
task