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

Cognitive Hallucination Mitigation on MME cognitive 12 (test)

124.5Commonsense Reasoning Score

IVE

70.9484.84598.75112.655Apr 2, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.04
124.549.598.561.5
2026.04
1234897.560
2026.04
122.54889.552
2026.04
12248.59153.5
2026.04
121.547.58951.5
2026.04
12146.59659.5
2026.04
11945.594.557.5
2026.04
1184092.555
2026.04
95.5110.5103.572.5
2026.04
94.5109.510270.5
2026.04
93.51099359
2026.04
93108.592.557.5
2026.04
92107.591.556.5
2026.04
91.5102.510070
2026.04
90.510198.565
2026.04
8810597.567.5
2026.04
79.5103.5188.5146.5
2026.04
78100.5177.5138.5
2026.04
78101.5187145
2026.04
77.5101180140
2026.04
77100176.5137.5
2026.04
75.598.5187.5144.5
2026.04
74.598.5182.5142
2026.04
7395185140