Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-image Reasoning on MuirBench

77.2Accuracy

L2-VMAS

17.71233.15648.664.044Jan 8, 2026Jan 11, 2026Jan 15, 2026Jan 19, 2026Jan 23, 2026Jan 27, 2026Jan 31, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
77.2------------
2026.01
75.5------------
2026.01
73------------
2026.01
71.6------------
2026.01
71------------
2026.01
68------------
2026.01
6844.5156.1251.2849.1588.6960.295686.8523.4471.5136.980.14
2026.01
67.9------------
2026.01
67.4------------
2026.01
64.5------------
2026.01
64.1------------
2026.01
62.3------------
2026.01
58.254.885064.160.6868.3457.355059.055066.1348.8150
2026.01
57.9------------
2026.01
57.8154.275058.9755.1365.8352.655063.585074.1946.4350
2026.01
56.6------------
2026.01
55.9------------
2026.01
51.3------------
2026.01
51.2------------
2026.01
51.1------------
2026.01
49.3535.9841.3347.4428.6364.8245.294866.5912.559.1428.5743.84
2026.01
44.8------------
2026.01
44.7739.6346.9444.8742.7452.2644.122755.1712.567.7430.9524.32
2026.01
44.5------------
2026.01
44.5------------
2026.01
44.533.5448.4738.4638.4667.5928.822653.8818.7556.9926.1935.62
2026.01
43------------
2026.01
41.8------------
2026.01
41.7------------
2026.01
39.8838.4149.4942.3140.639.731.762651.5112.568.2832.1419.18
2026.01
39.7------------
2026.01
37.9------------
2026.01
34------------
2026.01
33.6------------
2026.01
33.1------------
2026.01
32.5------------
2026.01
32.3------------
2026.01
31.1------------
2026.01
31.1------------
2026.01
27.4------------
2026.01
27.2------------
2026.01
26.8------------
2026.01
26.0826.2217.8639.7421.7925.3827.652124.7815.6256.4526.1917.12
2026.01
24.3------------
2026.01
23.4627.4422.9624.3623.0825.13202023.4923.4434.9514.2919.86
2026.01
22.3------------
2026.01
20.8526.2216.3341.0314.119.619.711321.3412.541.416.6715.75
2026.01
20------------