Benchmarks

CWE-Bench

Codingunit % · normalized over [0, 60]

CWE-Bench, run by Collinear — an external benchmark for automated vulnerability patching across CWE classes. Reported as pass@1.

#ModelSourceScoreNormalized

Score distribution

1 tracked result across the normalization window

060

Score vs. parameters

Open-weights models, log-x params

No open-weights models with disclosed parameter counts have a score here yet.