Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software Engineering Skill Evaluation on SWE-Skills-Bench (slo-implementation)
Loading...
60
Pass Rate (out of 10)
S2L
39.2
44.6
50
55.4
Jun 15, 2026
Pass Rate (out of 10)
Spearman Correlation (ρ)
CNG Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass Rate (out of 10)
Spearman Correlation (ρ)
CNG Score
S2L
Setting=Our method
2026.06
60
-0.0251
7.96
Vanilla LLM
Setting=Vanilla baseline
2026.06
40
-
-
Full Skill Text
Setting=Full Skill Tex...
2026.06
40
0.1566
0
Feedback
Search any
task
Search any
task