Qwen Code achieves 100% score on SWE-bench Verified
DennisYu07 · ghdev · 2026-08-15
Qwen Code released its test results on the SWE-bench Verified dataset.
Details
- Model Version: Qwen Code v0.21.12 (based on Qwen3.7-plus)
- Dataset: SWE-bench Verified (swe-bench/swe-bench-verified@2)
- Results: 1 resolved, 0 unresolved, 0 execution errors
- Final Score: 100.00%
This result indicates the model's high pass rate in handling real-world GitHub issues and code repair tasks.
More from coding & agent
- Steve Yegge's Beads agentic memory layer hits 1.5M downloads one year after launch — doodlestein · 2026-10-16
- Sakana AI open-sources AI-Scientist-v3, orchestrating coding agents to automate scientific discovery — cong_ml · 2026-10-16
- Coding agents keep opening 3 stacked PRs per chat, and merging them is a nightmare — holdenmatt · 2026-10-16
- Google-led paper uses sequential auctions to organize decentralized LLM agent workflows — _onionesque · 2026-10-16
- Since OpenAI's math release, GitHub contributors keep driving down the integer-multiplication kappa — xennygrimmato_ · 2026-10-16
- Pattern MCP makes coding agents check existing components before writing new code — DonR954 · 2026-10-16