OpenAI Blog company blog
SWE-bench Verified no longer measures frontier coding capabilities
SWE-bench Verified is increasingly contaminated and mismeasures frontier coding progress. Our analysis shows flawed tests and training leakage. We recommend SWE-bench Pro.
- Points
- 343
- HN comments
- 181
- Submissions
- 1
- Cited by
- 7 commenters
AI & Machine LearningSoftware Engineering2026
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Apr 26, 2026 | SWE-bench Verified no longer measures frontier coding capabilities by kmdupree | 343 | 181 |
Cited in comments
Linked from 10 Hacker News comments by 7 different people, from Mar 2026 to Jul 2026.
Most recent:
- stared · Jul 18, 2026
- stared · Jul 16, 2026
- robertkarl · May 28, 2026
- stared · Apr 24, 2026
- yfontana · Apr 23, 2026