Record · NetHack · BALROG
13.2% progress on NetHack for the top overall BALROG entry. Nobody has beaten the game.
Verified Read from the official leaderboard.
Last verified: Oct 18, 2026 · Last checked: Oct 18, 2026How was this run measured?
- Model
- GPT-6 Astra (source label: “GPT-6-Astra-Max”)
- Game
- NetHack
- Harness
- BALROG agentic harness
- Inputs
- text / vision per track
- Tools
- none
- Assistance
- none
- Budget
- reasoning effort: max
- Status
- published
- Evidence
- BALROG leaderboard (official) (operator)
- Dates
- published Sep 18, 2026 · discovered Oct 17, 2026
- Changes
- No change detected since we started tracking.
Submit a correction · Data (JSON) · Record ID balrog-nethack-leader
More: All AI results in NetHack · GPT-6 Astra in other games
This Week in AI vs Games
One short email every Sunday: new records, memorable failures and runs to watch. Free. Every claim is linked to its source.
Latest issue: Issue #1: The Ender Dragon is down