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

Spatial Reasoning on SPAR-Bench tiny

72.32Medium Difficulty Score

Human Level

4.730422.277739.82557.3723Dec 4, 2025Dec 19, 2025Jan 3, 2026Jan 18, 2026Feb 2, 2026Feb 17, 2026Mar 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
72.3267.2755.3172.7574.2528.7536.2578.2552.2566.533.5926460.9776.22809470928078825060
72.3267.2755.3172.7574.2528.7536.2578.2552.2566.533.5926460.9776.22809470928078825060
38.2532.7431.1943.0943.5117.3813.0541.930.9927.432.1729.0126.755932.2952.9450.628.2526.9226.5926.3426.7426.4925.77
2025.12
24.9336.3929.2553.8451513.637.434.423.424.4301628.845.11646458464632443022
2026.03
24.9336.3929.2553.8451513.637.434.423.424.4301628.845.11646458464632443022
2025.12
23.3935.6235.2845.449.813.81054.649.436.822.4421810.1640606850384418281836
2026.03
23.3935.6235.2845.449.813.81054.649.436.822.4421810.1640606850384418281836
2025.12
23.0539.435.3553.246.817.82949.657.414.414.6401613.1648.44747460565020342444
2026.03
23.0539.435.3553.246.817.82949.657.414.414.6401613.1648.44747460565020342444
22.65----------24.5-25.0923.8222.0231.2525.2722.1625.8124.4224.1726.89-
2025.12
7.3321.7725.434145.411.212.242.619.6265.4166023.3340482236141220612
7.3321.7725.434145.411.212.242.619.6265.4166023.3340482236141220612