Benchmark
OSS-Fuzz · Vulnerability Identification
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 1
- Scores recorded
- 1
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 79.4%
- Mean
- 79.4%
- Median
- 0%
- Std dev
- 79.4%
- 10th percentile
- 79.4%
- 90th percentile
- 79.4%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5Anthropic Opus 5 launch chart · OSS-Fuzz· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 79.4% |