Qwen3.8 Launch - QwenQoderBench: leaderboard
Alibaba Qwen's in-house coding benchmark for the user experience of its Qoder coding tool, from the Qwen3.8-Max launch post: models run in the Claude Code harness with a 6-hour timeout, 32,768 output tokens, temperature 1.0 and a 256K context window. Score is avg@5 in percent, higher is better; Claude Fable 5 results may involve fallbacks.
Metric: avg@5 Score (%). Source: qwen.ai. Saturation forecast: Around October 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 | 63.1 | #20 |
| 2 | Claude Opus 4.8 | 62.7 | #39 |
| 3 | Qwen 3.8 Max | 58.4 | #34 |
| 4 | GPT-5.6 Sol (Max) | 53.8 | #22 (GPT-5.6 Sol) |
| 5 | Qwen 3.7 Max | 36.8 | #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-qwenqoderbench · How It Works · Data refreshed daily, snapshot 2026-11-05.