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

Long-horizon tasks on Minecraft Gold

21.69Success Rate (SR)

EvoAgent

-0.86764.988710.84516.7013Feb 9, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.02
21.6930.48
2025.02
10.628.03
2025.02
8.849.76
2025.02
6.6110.69
2025.02
6.578.05
2025.02
00
2025.02
00