Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Routing on SWE-Bench Verified n=500
Loading...
92.1
QR (%)
OpenRouter Auto
75.356
79.703
84.05
88.397
May 16, 2026
QR (%)
CS (%)
MR (%)
Updated 15d ago
Evaluation Results
Method
Method
Links
QR (%)
CS (%)
MR (%)
OpenRouter Auto
Model Pool (strong → c...
2026.05
92.1
0.1
76
RouteLLM (BERT)
Model Pool (strong → c...
2026.05
91.1
18.6
45.2
HyDRA (cons.)
Model Pool (strong → c...
2026.05
86.1
54.1
70.4
HyDRA (agg.)
Model Pool (strong → c...
2026.05
84.5
63.7
52.8
Avengers Pro
Model Pool (strong → c...
2026.05
83.3
51
50.8
Azure Foundry Router
Model Pool (strong → c...
2026.05
76
66.2
17.6
Feedback
Search any
task
Search any
task