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

Multi-image Reasoning on DEMON

38.94Accuracy

Brote-IM-XXL

23.932827.828931.72535.6211Feb 19, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.02
38.94
2024.02
38.94
2024.02
38.7
2024.02
38.7
2024.02
38.14
2024.02
38.14
2024.02
37.34
2024.02
37.34
2024.02
37.33
2024.02
37.33
2024.02
37.22
2024.02
37.22
2024.02
36.37
2024.02
36.3
2024.02
36.3
2024.02
33
2024.02
33
2024.02
32.59
2024.02
32.59
2024.02
24.51
2024.02
24.51