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

Multimodal Hallucination Evaluation on MME

720Total Score

CAI

419.7832497.7241575.665653.6059Apr 27, 2026May 7, 2026May 18, 2026May 28, 2026Jun 8, 2026Jun 18, 2026Jun 29, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.06
720----
700----
2026.04
698.33195170148.33185
2026.06
691.66----
2026.06
685----
2026.04
673.33190165143.33175
2026.05
641.66195153.33133.33160
2026.05
636.66185143.33143.33165
2026.05
631.66195158.33123.33155
2026.05
629.99195158.33123.33153.33
2026.05
629.99195158.33123.33153.33
2026.04
626.66185130131.66180
2026.05
626.66190150121.66165
2026.05
624.99185151.66133.33155
2026.05
621.66190153.33118.33160
2026.05
614.99190163.33118.33143.33
2026.05
609.99195131.66133.33150
2026.05
599.99195136.66123.33145
2026.04
568.33180128.33120140
2026.04
516.66168.33121.66116.66110
2026.04
497.33168.33110113.66105.33
2026.04
485158.33111.33113.66101.66
2026.04
44615098.3393.33104.33
2026.04
431.33158.3391.339091.66