Benchmark
QwenSWEBench
What is QwenSWEBench?
QwenSWEBench is Qwen's software-engineering agent benchmark for repository-level issue resolution. Benchmark Radar tracks 2 reported scores for QwenSWEBench…
- Modality
- text
- Evaluates
- agents, code
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 2
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/qwen-swe-bench?top_n=500
QwenSWEBench results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.8 Max | Qwen | 0.807 | 2026-08-02 | evidence |
| Qwen3.8-27B | Qwen | 0.79 | 2026-08-14 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.