Qwen vs Deepseek: One wins with half the token price.
Models tested - Model A : Qwen3.8 Flash qwen3.8-flash , run through oh-my-pi omp , thinking level medium - Model B : DeepSeek V4.1 Flash deepseek-v4.1-flash , r
Alibaba's flagship 2.4T-parameter MoE model (95B active) with a 1M-token context, native image/video understanding, and strong agentic coding; first Max-class Qwen with open weights.
“Kimi K3, GLM-5.3, and Qwen3.8-Max will happily hack anything you ask them to. These are near frontier models and are incredibly competent.”
“Qwen3.8-Max is the only thing that comes close to Kimi K3. We need competition in the open-weights space.”
“Even the 3.8 max preview is useless... they forget instructions, they don't care about what the user asks for.”
Plutôt non — Qwen 3.8 Max n'a qu'un score worth-it de 43%, basé sur 244 votes de la communauté.
Qwen 3.8 Max est un modèle de Chat. Alibaba's best model yet, and the Chinese + English mix is finally balanced.
$2/$6 per 1M tokens
Models tested - Model A : Qwen3.8 Flash qwen3.8-flash , run through oh-my-pi omp , thinking level medium - Model B : DeepSeek V4.1 Flash deepseek-v4.1-flash , r
Mixture-of-Experts MoE is particularly interesting because sparse expert activation can reduce inference compute. But multimodal and MoE are not alternatives. O
I ran one real build in ohmypi omp : qwen3.8-max as the orchestrator, qwen3.8-flash as the executor. Below is what happened in that session, with the numbers th