Benchmark

QwenSWEBench

QwenSWEBench is Qwen's software-engineering agent benchmark for repository-level issue resolution.

Modality
text
Categories
agents, code
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Qwen3.8 MaxQwen0.8072026-08-02evidence
Qwen3.8-27BQwen0.792026-08-14evidence

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.