Kimi K3.1 vs Opus 5.5
I decided to create the legendary horror game Backrooms and show how the AI models coped with it
I'm a little upset with the result of the Kimi k3.1 game model itself, but there is something there
Kimi k3.1 - 40 minutes
Opus 5.5 - 1 hour 1 minutes
which model did it better?
Day 16/
You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.
