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

Real-world Visual Question Answering on RealWorldQA

79.35Accuracy

Qwen 3.5

64.11468.069572.02575.9805Dec 5, 2024Mar 9, 2025Jun 12, 2025Sep 14, 2025Dec 18, 2025Mar 22, 2026Jun 25, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.05
79.35--
2025.12
77.8--
2025.12
77.5--
2025.12
77.3--
2024.12
75.4--
74.9--
2026.04
74.9--
2025.12
74.8--
2026.06
73.9--
2025.12
73.5--
2025.12
72.5--
2026.04
72.5--
2025.12
72.3--
2024.12
71.9--
2025.12
71.9--
2024.12
71.8--
2026.02
71.6--
2026.04
71.6--
2026.05
71.38--
2026.06
71.2--
2025.12
71.1--
2026.06
71.1--
2026.06
70.9--
2026.05
70.85--
2025.12
70.8--
2025.12
70.7--
2025.12
70.6--
2025.12
70.6--
2026.02
70.6--
2026.03
70.59--
2026.02
70.5--
70.4--
2025.12
70.2--
2024.12
70.1--
2025.12
69.9--
2025.12
69.9--
2025.11
69.9--
2024.12
69.7--
2026.02
69.7--
2024.12
69.5--
2026.02
69.2--
2026.04
69.15--
2025.12
69--
2026.06
69--
2026.04
68.76--
2025.11
68.7--
2024.12
68.6--
2026.02
68.6--
2025.12
68.5--
2025.12
68.5--
2025.12
68.4--
68.1--
68.1--
68.1--
2026.03
68.1--
2025.12
68--
2024.12
67.8--
67.8--
2025.12
67.7--
2026.02
67.7--
2026.03
67.58--
2025.12
67.5--
2026.04
67.5--
2026.04
67.5--
2026.06
67.5--
2026.03
67.45--
2026.03
67.45--
2026.04
67.32--
2026.05
67.32--
2026.04
67.3--
2024.12
67.1--
2026.04
67.1--
2026.04
66.93--
2026.04
66.8--
2026.04
66.7--
2026.04
66.7--
2026.03
66.67--
2026.04
66.4--
2024.12
66.3--
2025.12
66.3--
2025.12
66.3--
2026.05
66.27--
2026.04
66.1--
2025.12
66--
2026.04
65.9--
2026.03
65.88--
2026.04
65.75--
2026.03
65.62--
2024.12
65.6--
2026.04
65.6--
2026.03
65.49--
2024.12
65.4--
2025.12
65.4--
2025.12
65.2376.52-
2025.12
65.177.38-
2025.12
65--
2025.12
65--
2026.04
65--
2026.04
64.8--
2026.04
64.7--
Showing 100 of 213 rows