Hacker News new | past | comments | ask | show | jobs | submit
dom96 | on: Kimi K3.1 Pro and K3.1 Pro Highspeed
yeah, it performed best for whatever reason. More specifically, it managed to deduce the meaning of the hack statement in the language better than Opus 5.5 did.
epolanski | parent
How many runs you make for each model?

Do you report an average score or the highest.

dom96 | root | parent
2 runs for each task, for each task it's either a pass/fail (the small green/red dots show each task pass/fail)