Benchmark
Capture-the-Flag Challenges
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 5
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 87.9%
- Mean
- 88.1%
- Median
- 5.9%
- Std dev
- 85.2%
- 10th percentile
- 96.7%
- 90th percentile
- 77.6%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 SolOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 96.7% |
| 2 | GPT-5.6 TerraOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 91.8% |
| 3 | GPT 5.5expanded internal hardest CTF set · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88.1% |
| 4 | GPT 5.5OpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88.1% |
| 5 | GPT-5.6 LunaOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.2% |
| 6 | GPT-5.3 CodexCybersecurity CTF challenges · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 77.6% |