BALROG NetHack results questioned: worse than last week's numbers?

mitrma · x · 2026-09-19

In the BALROG NetHack eval discussion, a participant questions creusroger's posted results: were they run with a default harness, and why do they seem worse than the results he was sharing last week? The point is made that BALROG assesses zero-shot performance—but who has ever beaten NetHack on their first attempt, even with wiki usage?

Related event: BALROG NetHack benchmark debate: harness self-modification and degenerate solutions(7 posts)→

Original post →

More from Research

Research channel →