Question mark says they are updated every minute, even gives you a prompt.
Watching for several minutes, none of then was good except Kimi K2. Sure, not every time, but solid third of them was actually working, while the others scored a perfect 0.
Also, as a Kimi K2 user (because Kagi), I approve. I don’t use Kimi K2 for coding, though, because JetBrains doesn’t offer that, but I use it in Kagi Assistant.
I ran into the same thing - they seem to change (potentially to other outputs from the same model?) when you click on the Question mark and go back.
Question mark says they are updated every minute, even gives you a prompt.
Watching for several minutes, none of then was good except Kimi K2. Sure, not every time, but solid third of them was actually working, while the others scored a perfect 0.
Also, as a Kimi K2 user (because Kagi), I approve. I don’t use Kimi K2 for coding, though, because JetBrains doesn’t offer that, but I use it in Kagi Assistant.
deepseek v3.1 had an (almost) perfect clock once for me.