Last month I used Copilot heavily, much much more than I usually do, but did not manage to use more than 58%.
Last month I used Copilot heavily, much much more than I usually do, but did not manage to use more than 58%.
Forced me to switch to OpenCode Go (not Zen), which isn't quite as nice as Copilot Chat deeply integrated into VSCode / Intelli but the models (DeepSeek v4 Pro, GLM 5.1, & Qwen 3.7 Max) are able replacements for Claude Sonnet 4.x / GPT 5.x while being way cheaper (especially DeepSeek).
Easily 7x or more for what amounts to self–serving work. At this point, we might just switch to 4.8 Opus.
Honestly, I would not spend a cent of my own money on a model that won't run on my PC, but still I feel like this is the end of this Microsoft product I hadn't used a month ago. We'll see if our sugar daddies keep funding it.
I swear I did few tests and it's rare you need more than medium on mundane job work.