Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Long-horizon game playing on BALROG NetHack

6.8Progression Rate

Gemini-3-Pro

-0.2721.5643.45.236Jul 1, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.07
6.8
2026.07
2.6
2026.07
2
2026.07
1.85
2026.07
1.7
2026.07
1.57
2026.07
1.4
2026.07
0.42
2026.07
0.3
2026.07
0
2026.07
0
2026.07
0