Early stress tests say Qwen3.8-Max matches DeepSeek-level performance

gerardsans · x · 2026-08-04

Qwen3.8-Max’s early stress tests reportedly match DeepSeek performance

The poster says they are trying out Qwen3.8-Max and that initial stress tests appear to reach DeepSeek-level performance without any significant degradation.

The post is short and informal, but the substance is a model comparison claim: an early hands-on impression that the new Qwen variant is holding up well under test. The author also asks what personal evals others use when trying new models.

Related event: Qwen3.8-Max Initial Tests Show Performance on Par with DeepSeek(2 posts)→

Original post →

More from Models

Models channel →