GPT Astra 6 hits new BALROG heights with 13% NetHack progression, still "not AGI"

_rockt · x · 2026-09-19

BALROG's leaderboard adds three new entries: GPT 5.6 Sol at max effort remains within error of Gemini 3 and 3.1 Pro, while GPT Astra 6 at max reasoning effort reaches new heights, posting 13% average progression on the NetHack Learning Environment. Researcher rockt comments: "Great progress. Not yet AGI though."

Original post →

More from Models

Models channel →