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

Spatial Reasoning on MMSI-Bench (test)

52.8PR Score

GCA

22.95230.70138.4546.199Nov 27, 2025Dec 9, 2025Dec 21, 2025Jan 3, 2026Jan 15, 2026Jan 27, 2026Feb 9, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2025.11
52.84544.7-47.6
2026.02
42.947.63640.442
2026.02
42.9503840.942.7
2025.11
3936.233.3-36.9
2025.11
35.92621-29.8
2025.11
35.636.929.3-33.8
2025.11
33.74023.3-32.6
2026.02
33.338.524.728.831.8
2026.02
313020.723.227.8
2026.02
30.826.92626.828.8
2025.11
30.525.422-27.8
2026.02
30.533.818.724.728
2026.02
30.520.823.324.727
2025.11
30.323.316-25.4
2026.02
30.325.42221.726.7
2025.11
29.826.926-27.3
2026.02
29.333.838.731.331.7
2025.11
29.129.421.9-26.9
2025.11
29.127.726-27.8
2025.11
28.928.822.5-28.9
2026.02
28.726.220.728.327.1
2025.11
28.525.418-26.1
2026.02
28.421.529.325.827.1
2025.11
2832.336-30.3
2026.02
2821.514.722.724.1
2026.02
27.819.223.325.825.6
2026.02
25.926.928.727.326.7
2025.11
24.523.122.7-25.3
2026.02
24.123.126.720.223.6