Collinear AI
CWE-bench v2
Defensive vulnerability patching on 250 audit-and-patch tasks spanning 185 weakness types, 100 public and 150 held out.
ModelsModels with a result.11
Top-3 spreadPoints from first to third.2.1 pts
YearYear of release.2026
Result and price
10 of 11 results
Results
11 results#ModelResultThe score from the source.
