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

Question Answering on ScienceQA

96Accuracy

LLaVA-OneVision-7B

42.12856.11470.184.086Nov 11, 2023Apr 3, 2024Aug 25, 2024Jan 16, 2025Jun 9, 2025Oct 31, 2025Mar 25, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2024.08
96
2026.03
94.33
2026.03
94.15
2026.03
93.82
2026.03
93.79
2023.12
90.9
2024.08
90.3
2026.02
89.06
2026.02
89.01
2026.02
88.86
2023.12
88.8
2023.12
88.7
2026.02
88.48
2026.02
87.45
2026.02
86.32
2026.02
86.06
2026.02
85.93
2024.11
84.2
2023.12
81.6
2023.12
79.5
2024.11
79
2024.11
77.3
2024.08
75.7
2024.11
73.2
2026.01
73
2026.01
73
2026.03
72.9
2026.01
72
2026.03
71.85
2023.12
71.6
2026.03
71.53
2026.03
71.32
2026.03
71.11
2026.03
70.69
2024.11
70.1
2026.03
70.06
2026.03
69.75
2026.03
69.43
2023.11
69.4
2026.03
69.16
2024.11
69.1
2026.03
68.91
2026.02
68.75
2023.12
68.7
2023.11
68.7
2024.11
68.3
2023.11
68.2
2026.03
67.44
2026.03
67.33
2024.08
67.2
2023.12
67.1
2023.11
67.1
2026.01
67
2023.12
66.8
2024.03
66.8
2023.11
66.8
2026.02
66.79
2026.03
66.49
2026.02
66.25
2026.03
66.05
2026.02
66.01
2026.02
65.96
2026.02
65.52
2026.02
65.23
2026.02
64.94
2024.03
64.9
2023.11
63.1
2026.03
62.95
2024.06
62.7
2026.03
62.24
2024.06
62.2
2024.03
61
2023.11
61
2024.03
60.5
2024.11
59.3
2024.11
49.2
2024.03
44.2