Qwen Code Achieves 100% Score on SWE-bench Verified Test
DennisYu07 · ghdev · 2026-08-19
A smoke test run for Qwen Code (v0.21.13, model qwen3.7-plus) on the SWE-bench Verified benchmark resulted in success. Using the dataset swe-bench/swe-bench-verified@2, the test completed 1 case with 1 resolved, 0 unresolved, and 0 execution errors, achieving a score of 100.00%. This verifies its bug-fixing capabilities within an isolated DSW EAS network environment.
More from coding & agent
- Agentic coding accessibility will reshape understanding of software complexity — pixlpa · 2026-08-24
- Devin Agent bypasses Slack block by finding emails in git logs — sandylikesfrogs · 2026-08-24
- Developer habits shift: Agents become collaborators from simple tools — latticecut · 2026-08-24
- Dev bottleneck shifts from writing to reading code: exe.dev co-founder — thursdai_pod · 2026-08-24
- The biggest AI mistake: trying to reinvent the wheel instead of using tools — Tired40s · 2026-08-24
- DeepPaperNote turns research papers into Obsidian notes — tom_doerr · 2026-08-24