Qwen 3.8 Max Preview Benchmarks Leaked
bdsqlsz · x · 2026-07-19
The Qwen 3.8 Max preview reportedly shows strong performance in internal benchmarks:
- It first took a "candy test," leading the author to believe its math capabilities have surpassed GPT 5.5 high and Kimi K3.
- Cited claims indicate Qwen3.8-Max trails Fable 5 by only 12.6 points in coding; in the Cowork test featuring 400 real-world agent tasks, it has already beaten Opus 4.8 Max.
- In specific results, Qwen leads Opus 4.8 Max by 5 points in Cowork tasks, also outperforming Kimi K3, GLM-5.2, and the previous-gen Qwen3.7-Max.
- The original post stresses this is merely a preview, with some prepped improvements yet to be deployed, meaning the final release could be even stronger.
Related event: Leaked Alibaba Qwen 3.8 Max Shows Strong Benchmark and Coding Performance(6 posts)→
More from coding & agent
- Reticle builds a verification layer that lets AI coding agents check their own generated code — Scobleizer · 2026-10-27
- Trust your agent, but read its logs: Claude managed agents tips — brada · 2026-10-27
- Dev training a guard model to block prompt injection, tool and memory poisoning — gnukeith · 2026-10-27
- Dev trains a ~4GB-VRAM sentinel model to guard against prompt injection and poisoned memory — gnukeith · 2026-10-27
- Superset rebrands as Paradev, raises $11.5M seed led by USV — massimosgrelli · 2026-10-27
- Ex-Big Tech managers may thrive in the AI era: manage agents like you managed teams — lxfater · 2026-10-27