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

Pairwise Human Preference Study on Minecraft real chunks (val)

67.1Win Rate

MD4

48.69253.47158.2563.029Apr 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
67.1
2026.04
57.1
2026.04
55.2
2026.04
55.2
2026.04
53.3
2026.04
49.4