Software engineering

QwenSWEBench

Qwen's in-house coding benchmark for evaluating a model's ability to complete software-engineering work. Higher is better.

Rankings

Higher is better

QwenSWEBench — frequently asked questions

What is QwenSWEBench?
Qwen's in-house coding benchmark for evaluating a model's ability to complete software-engineering work. Higher is better.
Which AI model scores highest on QwenSWEBench?
Qwen3.8-27B by Qwen holds the best QwenSWEBench result among tracked models, at 79% (released Aug 14 2026). Higher scores are better on this benchmark.
What are the top 1 models on QwenSWEBench?
1. Qwen3.8-27B (Qwen) — 79%.
How many models have a published QwenSWEBench score?
1 tracked model has a published QwenSWEBench score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.
What is the best open model on QwenSWEBench?
Qwen3.8-27B by Qwen is the highest-ranked model with downloadable weights on QwenSWEBench, scoring 79% at rank 1 overall.
← All benchmarks