Hacker News new | past | comments | ask | show | jobs | submit
Here are the results from the Pac-Man bench. It does pretty well for the price, around Sonnet 5.5.

Kimi K3.1 Pro ties Sonnet 5.5 at 93, for $0.68 and 11 min vs Sonnet's $1.61 and 14 min.

Kimi K3.1 Pro: https://jonclegg.github.io/pacman-bakeoff/#kimi-k3.1-pro

Claude Sonnet 5.5: https://jonclegg.github.io/pacman-bakeoff/#claude-sonnet-5-5

Interestingly, the Kimi one seems to implement the safe spot bug from the arcade original [1], while the Claude one doesn’t.

The prompt says that the agent shouldn’t look up existing implementations on the internet, so I’m guessing that the implementation is baked in?

[1] https://strategywiki.org/wiki/Pac-Man/Tips

On mobile Kimi definitely wins from the UX point of view
loading story #50216940
Until I looked, I thought I'd see Kimi vs Claude competitive gaming with pacman.

That would have been interesting to watch, which model gets the highest score.