Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multimodal Reasoning on MMMU-Pro

55Std-10 Score

Claude-3.5-Sonnet

14.4424.9735.546.03Dec 6, 2024
Updated 2d ago

Evaluation Results

MethodLinks
554851.5
5449.751.9
2024.12
51.445.948.6
49.444.446.9
2024.12
49.243.346.2
2024.12
484446
2024.12
41.93840
2024.12
41.632.637.1
2024.12
38.230.434.3
2024.12
382431
2024.12
36.42932.7
2024.12
36.332.134.2
2024.12
35.914.125
2024.12
34.12730.5
2024.12
32.827.130
2024.12
32.525.429
30.224.227.2
29.519.924.7
2024.12
28.221.324.7
2024.12
27.320.123.7
2024.12
26.313.119.7
2024.12
25.317.221.2
2024.12
23.315.519.4
2024.12
21.614.918.2
2024.12
1613.614.8