Benchmark
OpenAI Internal Research Debugging
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 4
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 59.2%
- Mean
- 67.8%
- Median
- 8.8%
- Std dev
- 50%
- 10th percentile
- 68.3%
- 90th percentile
- 50%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 SolOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 68.3% |
| 2 | GPT-5.6 TerraOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.8% |
| 3 | GPT-5.6 LunaOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50.8% |
| 4 | GPT 5.5OpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50% |