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

Spatial Reasoning on SPAR-Bench

67.3Overall Score

Human Level

18.9431.49544.0556.605Nov 20, 2025Dec 18, 2025Jan 16, 2026Feb 14, 2026Mar 15, 2026Apr 13, 2026May 12, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.05
67.3---
62.3---
2026.04
54.72---
2026.04
51.44---
2026.05
50.6---
49.42---
2026.04
42.77---
2026.05
42.6---
2026.04
42.4---
2026.04
41.6---
2026.05
41---
2026.05
39.2---
2026.04
39.03---
2026.04
38.26---
2026.04
38.05---
37.9---
2026.05
37.6---
2026.04
37.4---
2025.11
37.337.9136.82-
2026.05
36.9---
2025.11
36.6836.6336.72-
2026.05
36.4---
2025.11
36.3938.135.3-
2025.11
36.2835.9636.46-
2026.04
35.98---
35.3---
2026.04
35.1---
2026.04
34.98---
2025.11
34.6633.5135.41-
2026.05
34.4---
2026.04
34.2---
2026.04
33.19---
32.9---
2025.11
32.7332.5728.98-
2026.05
32.7---
2026.05
31.5---
2026.04
31.44---
2025.11
31.233.1329.92-
2026.05
31.2---
2026.04
30.6---
2025.11
30.08---
2026.04
26.53---
2026.05
24.6---
2026.05
21.8---
20.8---
2026.05
---42.4
2026.05
---20.8
2026.05
---32.9
2026.05
---35.3
2026.05
---34.2
2026.05
---37.4
2026.05
---37.9
2026.05
---69.2
2026.05
---67.3
2026.05
---32.7
2026.05
---50.1
2026.05
---49.8
2026.05
---55.1
2026.05
---48.7
2026.05
---33.8
2026.05
---39.1
2026.05
---39.6
2026.05
---38.2
2026.05
---33
2026.05
---32.9
2026.05
---34.2
2026.05
---37.9
2026.05
---46.6
2026.05
---40.8
2026.05
---68.2
2026.05
---54.3
2026.05
---58.4
2026.05
---64.3
2026.05
---38.1
2026.05
---36.3
2026.05
---33.1
2026.05
---39.8
2026.05
---34.1
2026.05
---32.1
2026.05
---43.7