Benchmark
SRE-Bench · 1 Attempt
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 3
- Scores recorded
- 3
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 52.1%
- Mean
- 55.9%
- Median
- 30.9%
- Std dev
- 12.5%
- 10th percentile
- 88%
- 90th percentile
- 12.5%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 Astra1 attempt· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88% |
| 2 | GPT-5.6 Sol1 attempt· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.9% |
| 3 | Claude Opus 51 attempt· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 12.5% |