Benchmark
SWE-Lancer IC Diamond
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
- 78%
- Mean
- 81.4%
- Median
- 3.4%
- Std dev
- 74.6%
- 10th percentile
- 81.4%
- 90th percentile
- 74.6%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.3 Codexxhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 81.4% |
| 2 | GPT 5.2xhigh · 40/237 infrastructure failures omitted· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74.6% |