Benchmark
SWE-Lancer offline accuracy
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
- Models measured
- 2
- Scores recorded
- 2
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 18.3%
- Mean
- 28.4%
- Median
- 10.2%
- Std dev
- 8.1%
- 10th percentile
- 28.4%
- 90th percentile
- 8.1%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | o1offline-198· SWE-Lancer offline leaderboard | 28.4% |
| 2 | GPT 4ooffline-198· SWE-Lancer offline leaderboard | 8.1% |
Data credits: SWE-Lancer community leaderboard. Offline task subset as sized in the publisher README; aggregate accuracy and earned payouts.