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

Multimodal Model Evaluation on MMBench Chinese

82.6Accuracy

SAIL-VL2

55.24862.34969.4576.551Nov 12, 2023Apr 1, 2024Aug 21, 2024Jan 10, 2025May 31, 2025Oct 20, 2025Mar 11, 2026
Updated 4mo ago

Evaluation Results

MethodLinks
2025.12
82.6
2024.02
82.1
2025.12
80.5
2025.12
79.3
2025.12
79.3
2025.12
78.9
2025.12
78.6
2025.12
78.3
2025.12
78
2025.12
77.7
2024.03
76.5
2025.12
74.2
2024.02
73.7
2024.03
73.7
2024.02
72.4
2024.03
72.4
2024.06
67.6
2024.06
66.1
2023.11
65.5
2023.12
65.4
2026.03
65.1
2024.03
64.8
2023.12
64.3
2024.02
64.3
2026.03
63.8
2024.03
63.6
2023.12
63.6
2024.02
63.6
2024.05
63.6
2024.01
63.6
2024.01
63.6
2024.03
63.6
2024.02
63.6
2026.03
63.5
2024.11
63.3
2024.02
62.8
2026.03
62.8
2026.03
62.6
2026.03
62.5
2026.03
62.5
2026.03
62.3
2024.02
62.2
2024.03
62.2
2024.06
62.2
2026.03
62.2
2024.11
62
61.8
2023.12
61.7
2024.06
61.7
2026.03
61.5
2026.03
61.3
2026.03
61.2
2026.03
61
2026.03
60.7
2024.03
60.6
2024.01
60.6
2024.06
60.6
2024.11
60.6
2026.03
60.4
2023.11
60.2
2026.03
59.8
2024.03
59.7
2023.11
59.5
2023.11
59.1
2024.03
58.6
2026.03
58.4
2023.11
58.3
2024.03
58.3
2023.12
58.3
2024.02
58.3
2024.01
58.3
2024.03
58.3
2024.06
58.3
2026.02
58.3
2026.02
58.2
2024.03
57.9
2024.06
57.9
2026.02
57.9
2024.06
57.6
2026.02
57.6
2026.02
57.6
2026.02
57.4
2026.02
57.3
2026.02
57.3
2026.03
57.3
2026.03
57.1
2026.02
57
2026.03
56.9
2023.11
56.7
2024.03
56.7
2023.12
56.7
2024.02
56.7
2024.01
56.7
2024.03
56.7
56.7
2024.06
56.7
2024.11
56.7
2026.02
56.7
2026.03
56.7
2026.03
56.3
Showing 100 of 154 rows