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

Spatial Reasoning on bAbI (test)

24Accuracy

Self-Consistency

-0.965.521218.48Feb 2, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
24
2026.02
22
2026.02
22
2026.02
22
2026.02
20
2026.02
20
2026.02
20
2026.02
20
2026.02
20
2026.02
18
2026.02
18
2026.02
14
2026.02
2
2026.02
2
2026.02
2
2026.02
0
2026.02
0
2026.02
0
2026.02
0
2026.02
0