# Anthropic OSS-Fuzz crash leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-anthropic-oss-fuzz-any-crash

Anthropic OSS-Fuzz Any-Crash Rate. Every model the catalog carries a published Anthropic OSS-Fuzz crash value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Any-crash rate |
| Tasks | Approximately 830 OSS-Fuzz entry points |
| Difficulty | Vulnerability discovery |
| Published by | [Claude Fable 5 and Claude Mythos 5](https://www.anthropic.com/news/claude-fable-5-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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Mythos 5](https://modelchoice.dev/models/claude-mythos-5) | Anthropic | 80.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
