Qwen3.8 Launch - QwenSWEBench: leaderboard
Alibaba Qwen's in-house software-engineering benchmark from the Qwen3.8-Max launch post: every model runs in the Claude Code harness with an 8-hour timeout, 32,768 output tokens, temperature 1.0 and a 256K context window. Score is avg@3 in percent, higher is better; the post notes that Claude Fable 5 results may involve fallbacks.
Metric: avg@3 Score (%). Source: qwen.ai. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 | 86.3 | #20 |
| 2 | Claude Opus 4.8 | 84 | #39 |
| 3 | Qwen 3.8 Max | 80.7 | #34 |
| 4 | GPT-5.6 Sol (Max) | 73.5 | #22 (GPT-5.6 Sol) |
| 5 | Qwen 3.7 Max | 63.4 | #85 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=qwen3-8-launch-qwenswebench · How It Works · Data refreshed daily, snapshot 2026-11-05.