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

Hallucination Evaluation on POPE v1.0 (test)

87POPE Score

MoE-LLaVA-2B

84.19284.92185.6586.379Mar 22, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.03
87--
2026.03
86.6--
2026.03
86.6--
2026.03
85.9--
2026.03
85.7--
2026.03
85.4--
2026.03
85.4--
2026.03
85.4--
2026.03
85.4--
2026.03
85.3--
2026.03
84.9--
2026.03
84.7--
2026.03
84.6--
2026.03
84.5--
2026.03
84.3--
2026.02
-85.987.08
2026.02
-85.9387.47
2026.02
-85.7287.05
2026.02
-86.9587.53
2026.02
-85.6986.98
2026.02
-87.1587.24