Hands-On Review and Benchmark: Qwen 3.8 Max

WorldofAI · youtube · 2026-07-20

This video puts the Qwen 3.8 Max Preview to the test. Marketed as Alibaba's new flagship LLM, it reportedly boasts a parameter size of 2.4 trillion and claims to rank just behind Fable 5.

Using a custom benchmark tool, the creator evaluates the model's performance in:

It is compared against Kimi K3 and GPT-5.6 Sol, wrapping up with the creator's verdict on its current tier.

Related event: Qwen3.8-Max Preview Tested: Strong Coding but Slow Thinking(13 posts)→

Original post →

More from Models

Models channel →