Agentic benchmark
CWE-Bench leaderboard
Every model the catalog carries a published CWE-Bench value for, ranked by that value.
CategoryAgentic
MeasurePass@1
TasksReal-world vulnerability patching tasks
DifficultyAutomated vulnerability remediation
Published byCWE-Bench leaderboard
An external benchmark for evaluating whether coding agents can produce correct patches for real-world software vulnerabilities.
CWE-Bench ranking
1 model with a published CWE-Bench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Pass@1 |
|---|---|---|---|
| 1 |  Gemini 3.8 Flash Cyber | 47.2 |
Evidence key: Observed
Rows are ordered by the value CWE-Bench leaderboard published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.