external benchmark
Anthropic OSS-Fuzz crash leaderboard
Anthropic OSS-Fuzz Any-Crash Rate. Every model the catalog carries a published Anthropic OSS-Fuzz crash value for, ranked by that value.
Categoryexternal
MeasureAny-crash rate
TasksApproximately 830 OSS-Fuzz entry points
DifficultyVulnerability discovery
Published byClaude Fable 5 and Claude Mythos 5
Share of evaluated OSS-Fuzz entry points where the model produced at least a crash.
Anthropic OSS-Fuzz crash ranking
1 model with a published Anthropic OSS-Fuzz crash 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 | Any-crash rate |
|---|---|---|---|
| 1 |  Claude Mythos 5 | Anthropic | 80.0 |
Evidence key: Observed
Rows are ordered by the value Claude Fable 5 and Claude Mythos 5 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.