Software engineering

QwenSWEBench V2

Qwen's in-house coding benchmark, second version, built around complex real-world software-engineering tasks. Scores are not comparable with the first version. Higher is better.

Rankings

Higher is better

QwenSWEBench V2 — frequently asked questions

What is QwenSWEBench V2?
Qwen's in-house coding benchmark, second version, built around complex real-world software-engineering tasks. Scores are not comparable with the first version. Higher is better.
Which AI model scores highest on QwenSWEBench V2?
Qwen3.8-Max-0902 by Qwen holds the best QwenSWEBench V2 result among tracked models, at 70% (released Sep 2 2026). Higher scores are better on this benchmark.
What are the top 2 models on QwenSWEBench V2?
1. Qwen3.8-Max-0902 (Qwen) — 70%; 2. Qwen3.8-Max (Qwen) — 55.1%.
How many models have a published QwenSWEBench V2 score?
2 tracked models have a published QwenSWEBench V2 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.