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

Spatial Reasoning (Granular Metrics) on MMSI-Bench

49.5Average Accuracy

MSSR

23.530.253743.75Oct 19, 2025Nov 10, 2025Dec 2, 2025Dec 24, 2025Jan 15, 2026Feb 6, 2026Mar 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
49.5----------5050.647.1
2026.03
41.94335.132.148.842.451.860.936.432.436.842--
2026.03
4145.239.43744.247.162.654.728.831.132.934.9--
2025.10
41----------34.945.836.4
2026.03
40.334.429.839.551.247.155.439.133.341.940.836.4--
2025.10
39.3----------32.342.338.6
2026.03
37.351.628.727.220.941.238.646.939.44638.236.4--
2025.10
37----------34.338.536.1
2026.03
36.939.731.939.545.335.243.351.521.236.430.234.3--
2025.10
35----------30.337.433.9
2025.10
32----------30.33331.4
2025.10
31.1----------27.832.830.3
2025.10
31.1----------30.332.628.9
2026.03
30.936.626.627.229.136.527.737.524.236.532.928.8--
2026.03
30.725.83434.623.334.136.145.327.32730.327.3--
2025.10
30.7----------27.331.232.1
2026.03
30.334.424.523.519.837.627.732.831.835.136.830.8--
2026.03
30.334.424.523.519.837.627.732.831.835.136.830.8--
2025.10
30.3----------30.82834.3
2025.10
30.2-------------
2025.10
28.9----------22.732.826.1
2025.10
28.7----------30.329.925.4
2026.03
28.534.423.432.112.837.626.537.519.728.431.629.3--
2026.03
28.523.722.339.529.131.842.235.919.717.626.327.3--
2026.03
28.44331.933.330.237.638.628.119.713.532.915.7--
2025.10
28----------19.729.531
2025.10
26.8----------29.325.527.5
2025.10
26.5----------23.229.523.2
2025.10
25.9----------25.825.926.1
2025.10
25.3----------25.825.523.9
2025.10
24.5----------19.226.923.9
2025.10
24.5----------11.62827.1