Qwen3-Coder
Alibaba·
LLMscodingcloud + local
Overview
Code-specialized model optimized for software engineering.
Capabilities and innovations
Code generationAgentic codingMulti-file editingTool useCode-specialized TrainingAgentic SWE PipelineMulti-file Context
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Verified | 52.7% | unsourced |
- GPQA Diamond: not reported by the vendor
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Pro: not reported by the vendor
- MMLU: not reported by the vendor
- MMLU-Pro: not reported by the vendor
- Terminal-Bench 2.x: benchmark did not exist at release
- MMMU-Pro: benchmark did not exist at release
Links
More from Alibaba
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.