Since opencode go's deepseek-v4-flash has shrunk significantly
Since opencode go's deepseek-v4-flash has shrunk significantly, the current price-performance ratio should be to subscribe to the chatgpt plus package, and then use gpt-5.6-luna max in the codex+deepseek harness👀 I have slowly started to move from codex to dsh
Qwen 3.8 27b
DeepSeek V4 Flash 0731 GPT 5.6 Luna Sub-models rarely pass this test.
Qwen 3.8 27b
DeepSeek v4 Flash 0731 GPT 5.6 Luna Luna looks the best.
Brothers, I really ran this DeepSeek Harness from scratch, not a cloud experience.
This issue is directly installed and tested completely. Web UI, remote access, multiple models, plug-ins, Agent mode, execution traces, Issue/PR analysis, session branches, all gone through. It's not the kind of thing that starts blowing after just opening the interface and taking a quick look at it. The most outrageous thing is that I also got DeepSeek V4…
You have reached the end of the archive
All of deepseek