Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Coding on SWE-Bench (Score, Relative Change)
Loading...
59
Score
SAR
56.504
57.152
57.8
58.448
Jul 3, 2026
Score
Relative Change (%)
Updated 18d ago
Evaluation Results
Method
Method
Links
Score
Relative Change (%)
SAR
Agent=ClaudeCode, Proj...
2026.07
59
1.72
Baseline (In-house)
Agent=ClaudeCode
2026.07
58
-
SAR
Agent=CodeAct, Project...
2026.07
57.4
1.41
Baseline (In-house)
Agent=CodeAct
2026.07
56.6
-
Feedback
Search any
task
Search any
task