SWE-bench Scores Went From 1.96% to 72.7%. The Benchmark Was Repaired In Between.
Article summary
Quick briefing — cleaned from the original RSS feed
In October 2023, a team at Princeton published a benchmark called SWE-bench: 2,294 software engineering problems drawn from real GitHub issues and their corresponding pull requests across 12 popular Python repositories. The paper reported that the best model of the day, Claude 2, resolved 1.96% of them. Not nineteen percent. One point nine six. In May 2025, Anthropic announced Claude Sonnet 4 with a score of 72.7% on SWE-bench Verified. The tempting sentence writes itself: models got…
1Key Takeaways
- In October 2023, a team at Princeton published a benchmark called SWE-bench: 2,294 software engineering problems drawn from real GitHub issues and their corresponding pull requests across 12 popular Python repositories.
- The paper reported that the best model of the day, Claude 2, resolved 1.96% of them.
- In May 2025, Anthropic announced Claude Sonnet 4 with a score of 72.7% on SWE-bench Verified.
- The tempting sentence writes itself: models got….
2AIWedia Score
8.3/10
High relevance — worth your attention today
Based on source trust, recency, category impact, and story depth.
3Why it matters
Coding AI shifts how fast software ships and how much human review each change needs. DEV — ML reports that in October 2023, a team at Princeton published a benchmark called SWE-bench: 2,294 software engineering problems drawn from real GitHub issues and their corresponding pull requests across 12 popular Python repositories.
Explore related
Browse toolsCoding AI news
Explore curated coding ai tools on AIWedia — compare, rank, and launch from our directory.
Full story on DEV — ML
Read full articleHeadlines aggregated via RSS for discovery on AIWedia. Original content © DEV — ML. We link to the source and do not republish full articles.