Anthropic OSS-Fuzz Write-Primitive-or-Higher Rate (Anthropic OSS-Fuzz write primitive)
We show this table for reference; we do not rank on it.
Share of evaluated OSS-Fuzz entry points where the model achieved a write primitive or stronger result.
Benchmark score on Anthropic OSS-Fuzz write primitive — September 29, 2026
We compile the Anthropic OSS-Fuzz write primitive rows from provider self-reports. Claude Mythos 5 leads the table at 32.4%. We do not use these results to rank models overall.
1 modelAgenticCurrentDisplay onlyUpdated September 29, 2026
Benchmark score table (1 model)
ScoreAbout Anthropic OSS-Fuzz write primitive
Year
2026
Tasks
Approximately 830 OSS-Fuzz entry points
Format
Write-primitive-or-higher rate
Difficulty
Vulnerability exploitation
Anthropic grades exploit severity on an internal five-tier ladder. BenchLM stores the reported write-primitive-or-higher rate as a separate display-only result.
Freshness and provenance
Version
Anthropic OSS-Fuzz write primitive 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does Anthropic OSS-Fuzz write primitive measure?
Share of evaluated OSS-Fuzz entry points where the model achieved a write primitive or stronger result.
Which model scores highest on Anthropic OSS-Fuzz write primitive?
Claude Mythos 5 by Anthropic currently leads with a score of 32.4% on Anthropic OSS-Fuzz write primitive.
How many models are evaluated on Anthropic OSS-Fuzz write primitive?
1 AI models have been evaluated on Anthropic OSS-Fuzz write primitive on BenchLM.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.