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

Perception and Reasoning on RealWorldQA

74.2Score

Qwen3.5-4B

47.607254.511161.41568.3189May 8, 2026May 14, 2026May 20, 2026May 27, 2026Jun 2, 2026Jun 8, 2026Jun 15, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
74.2
2026.05
73.8
2026.05
73.2
2026.05
71.2
2026.05
71
2026.06
71
2026.05
70
2026.06
69.5
2026.05
69.02
2026.05
69
2026.05
68.89
2026.05
68.5
2026.05
67.8
2026.05
67.71
2026.05
67.32
2026.06
67.3
2026.05
67.2
2026.05
67.19
2026.06
66.7
2026.06
66.4
2026.05
66.3
2026.05
66
2026.05
65.6
2026.05
65
2026.05
64.97
2026.05
64.45
2026.05
63.27
2026.05
63.01
2026.05
61.6
2026.06
61.6
2026.05
60.65
2026.05
60.4
2026.05
60
2026.05
56.34
2026.05
55.03
2026.05
52.55
2026.05
48.63