Benchmark
SRE-Bench · 4 Attempts
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 2
- Scores recorded
- 2
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 84%
- Mean
- 99.2%
- Median
- 15.3%
- Std dev
- 68.7%
- 10th percentile
- 99.2%
- 90th percentile
- 68.7%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 Astrawithin 4 attempts· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 99.2% |
| 2 | GPT-5.6 Solwithin 4 attempts· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 68.7% |