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

Multimodal Evaluation on MMBench CN

82.37Accuracy

Qwen2.5-VL-7B

48.289257.137165.98574.8329Jun 28, 2024Oct 19, 2024Feb 9, 2025Jun 3, 2025Sep 24, 2025Jan 15, 2026May 9, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.05
82.37
2026.05
81.94
2026.05
81.82
2026.05
81.71
2026.05
81.55
2026.05
81.38
2026.05
80.72
2026.05
80.72
2026.05
80.56
2026.05
80.31
2026.05
80.24
2026.05
80.06
2026.05
77.84
2026.05
77.59
2026.05
77.43
2026.05
76.6
2024.11
74.3
2024.11
71.8
2024.11
70.3
2024.11
70.1
2024.11
67.7
2025.10
63.7
2025.10
63.4
2026.02
63.3
2026.02
63.3
2026.02
63.1
2026.02
63.1
2026.02
62.9
2026.02
62.6
2026.02
62.6
2026.02
62.5
2026.02
62.5
2026.02
62.5
2026.02
62.5
2025.10
62.5
2026.02
62.3
2026.02
61.9
2026.02
61.9
2026.02
61.2
2025.10
60.8
2024.11
60.6
2026.02
60.6
2026.02
60.6
2024.06
59.9
2024.06
59.9
2026.02
59.9
2024.06
59.4
2024.06
59.3
2026.02
59.3
2024.06
59.1
2024.06
59.1
2024.06
59
2026.02
58.5
2026.02
58.5
2024.11
58.3
58.3
2026.04
58.3
2025.10
58.2
2026.03
58.1
2025.10
58.1
2025.10
58.1
2025.12
57.6
2025.10
57.6
2026.02
57.39
2026.03
57.3
2026.02
57.13
2026.03
57
2026.02
56.96
2026.03
56.9
2026.02
56.87
2026.02
56.87
2026.02
56.6
2026.02
56.4
2026.02
56.2
2026.02
55.9
2026.03
55.9
2025.12
55.8
2026.03
55.8
2026.03
55.8
2026.04
55.8
2026.03
55.5
2026.03
55.4
2026.03
55.3
2026.03
55.1
2024.11
54.9
2026.02
54.9
2026.02
54.4
2026.02
53.78
2026.03
53.6
2025.12
53.4
2026.04
52.8
2026.03
52.7
2026.02
52.3
2026.03
52.3
2026.03
52.3
2026.03
52.1
2026.02
51.72
2026.03
50.3
2026.04
50
2026.03
49.6
Showing 100 of 120 rows