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

Multi-modal Question Answering on MMMU (val)

70.7Accuracy

Proprietary API SOTA (Hurst et al., 2024)

35.54844.67453.862.926Jan 21, 2025Apr 9, 2025Jun 26, 2025Sep 12, 2025Nov 29, 2025Feb 15, 2026May 5, 2026
Updated 28d ago

Evaluation Results

MethodLinks
2025.01
70.7
2026.05
60.9
2026.05
60.7
2026.05
59.7
2026.05
58.7
2026.05
57.2
2026.05
57.2
2025.01
56.2
2026.05
56.1
2026.05
54.7
2026.05
51.8
2026.05
51
2026.05
48.8
2025.01
44.1
2025.01
42.9
2026.05
37.4
2026.05
36.9