Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software engineering agent task completion on SWE-Bench Verified
Loading...
78.2
Accuracy
LLM-as-a-Verifier
75.704
76.352
77
77.648
Jul 6, 2026
Accuracy
Pass@1
Oracle Success Rate
Updated 19d ago
Evaluation Results
Method
Method
Links
Accuracy
Pass@1
Oracle Success Rate
LLM-as-a-Verifier
2026.07
78.2
-
-
Opus 4.5
Baseline Rank=#1
2026.07
76.8
-
-
G3 Flash
Baseline Rank=#2
2026.07
75.8
-
-
M2.5
Baseline Rank=#3
2026.07
75.8
-
-
Candidate Pool
2026.07
-
76.1
84.4
Feedback
Search any
task
Search any
task