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)→
More from Models
- Ornith-1.5 Open Models Released, Claiming Claude Opus Performance — alejandroll10 · 2026-08-26
- 14-year AI veteran: Grok understood code I thought no one ever would — Kuprel · 2026-08-26
- Together Ranks Top Open Models: Kimi K3 and DeepSeek V4 Lead Use Cases — togethercompute · 2026-08-26
- Questions over Astra's progress: 2 months for 3 more models? — teortaxesTex · 2026-08-26
- View: Tokens-per-second matters more than model size now — natesiggard · 2026-08-26
- Tiel-Coder-35B achieves 121.4 tok/s for local inference — DerTomsn · 2026-08-26