Can Qwen 3.8 Preview Approach the Frontier?
teortaxesTex · x · 2026-07-20
This comment discusses the potential performance of Qwen 3.8 Preview.
The author suggests it needs to be at least stronger than 3.7 Max to be considered "decent," guessing it will likely land somewhere between GLM 5.2 or better. A cited viewpoint notes that the Qwen series often releases early open-weight versions that feel like "semi-finished" products, offering more scientific value. Meanwhile, it's acknowledged that Qwen 3.6 is clearly superior to 3.5, and while 3.7 Max is already approaching the frontier, Max preview versions generally deliver mediocre performance.
Related event: Qwen3.8-Max Preview Tested: Strong Coding but Slow Thinking(13 posts)→
More from Models
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11