Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software Engineering on SWE-Bench Lite (pass@1)
Loading...
33
Pass@1
LLM-as-a-Verifier
23.12
25.685
28.25
30.815
Jul 6, 2026
Pass@1
Updated 19d ago
Evaluation Results
Method
Method
Links
Pass@1
LLM-as-a-Verifier
Verification Budget=2N...
2026.07
33
Pairwise
Verifier=V1, Verificat...
2026.07
31
Pointwise
Mechanism=LM judge, Ve...
2026.07
29.7
Base model
Sampling Strategy=Best...
2026.07
23.5
Feedback
Search any
task
Search any
task