Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Bug-finding on OSV
Loading...
10
Reproduced Bugs Rate
CLAUDE CODE
7.92
8.46
9
9.54
Jun 17, 2026
Reproduced Bugs Rate
Newly Discovered Bugs Count
Total Bugs Found
Relative Improvement (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Reproduced Bugs Rate
Newly Discovered Bugs Count
Total Bugs Found
Relative Improvement (%)
CLAUDE CODE
Backing Model=Claude
2026.06
10
26
36
61
CODE-AUGUR
Backing Model=DeepSeek
2026.06
9
40
49
-
ATLANTIS
Backing Model=Claude
2026.06
9
20
29
86
CODE-AUGUR
Backing Model=Claude
2026.06
8
50
58
-
ATLANTIS
Backing Model=DeepSeek
2026.06
8
2
10
370
CLAUDE CODE
Backing Model=DeepSeek
2026.06
8
11
19
157
Feedback
Search any
task
Search any
task