Qwen3.8 family is my new favourite
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
Best core correctness on coding, 40% cheaper than Opus 5
“Yeah also with Opus 5.5 you still have to be really careful what you say and keep the context clean.”
“Opus 5.5 has no problem with Haskell in any domain whatsoever, including mixing it up with FFI and eDSLs. You call it, it does it.”
“What is going on? It is making wildly horrible, over-engineered, and just inaccurate code suggestions.”
Yes — Claude Opus 5.5 has a 67% worth-it score, based on 494 community votes.
Claude Opus 5.5 is a Chat model. Still the most reliable model for actually shipping code. It just doesn't hallucinate the way others do.
$4/$20 per 1M tokens
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
Model tested - Models: OpenAI GPT-6 Sol vs Anthropic Claude Opus - Use case: Coding, backend development, debugging, and AI agent workflows - Main evaluation cr