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

Multimodal Evaluation on SEED-Bench

77.3Accuracy

D2Dloc

47.1454.9762.870.63Jun 1, 2023Nov 2, 2023Apr 5, 2024Sep 7, 2024Feb 9, 2025Jul 14, 2025Dec 16, 2025
Updated 6d ago

Evaluation Results

MethodLinks
2025.07
77.3----
2025.12
77.01----
2025.07
77----
2025.12
76.64----
2025.07
76.6----
2025.07
76.5----
2025.07
76.5----
2025.07
76.4----
76.38----
2025.12
76.36----
2025.07
76.3----
2025.09
76.1----
2025.07
76.1----
76.05----
2025.07
75.6----
75.48----
75.47----
75.45----
75.34----
75.17----
2025.09
75.1----
75.1----
74.8----
74.64----
73.97----
2025.07
72----
2025.03
71.8----
2025.09
70.9----
2025.09
70.7----
2024.08
70.6----
2025.10
69.74---53.62
2025.10
69.52---53.01
2025.10
69.27---51.48
2025.10
68.76---52.31
2025.03
68.5----
2025.10
68.48---52.06
2025.03
68.3----
2025.10
68.11---51.65
2025.03
68----
2024.06
66.7----
2025.10
66.52---49.69
2025.10
66.51---49.66
66.5----
2025.10
66.26---49.54
2024.06
66.1----
2024.06
65.9----
2024.06
65.6----
2024.06
65.4----
2024.06
65.3----
2025.03
65----
2025.03
65----
2024.06
64.9----
2025.10
63.23---46.58
2025.10
63.01---45.95
2024.05
63----
2024.08
62.8----
2023.06
62.8----
2024.05
62.5----
2024.05
62.2----
2023.06
62.2----
2024.05
61.9----
2023.06
61.7----
2024.08
61.6----
2024.05
61.6----
2024.08
61.6----
2023.06
61.3----
2023.12
61.2----
2024.08
61.1----
2024.05
61.1----
2024.05
60.6----
2024.05
60.4----
2024.05
60.3----
2024.05
60.2----
2024.08
60.1----
2024.05
60----
2025.10
59.98---42.87
2025.10
59.76---42.61
2024.08
59.7----
2024.10
58.866.537.437.2-
2024.10
58.766.337.437.7-
2024.08
58.6----
2024.05
58.6----
2023.12
58.6----
2024.08
58.6----
2024.10
58.666.137.337-
2024.08
58.2----
2024.08
58.2----
2023.12
58.2----
2024.08
58.2----
2024.10
58.265.437.836.8-
2024.08
56.3----
2025.03
55.6----
2025.03
53.9----
2025.07
53.8----
2025.03
53.5----
2024.08
53.4----
2024.08
53.4----
2024.10
53.458.838.1--
2025.03
49.2----
2025.03
48.3----
Showing 100 of 112 rows