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

World Knowledge Reasoning on WISE random subset of 200 samples

94Cultural Accuracy

GPT-4o

9.7631.6353.575.37Apr 8, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.04
94649893989589
2025.04
56576248634255
2025.04
56556249634155
49585543483349
2025.04
48586242513550
45504849563447
2025.04
44505844523146
2025.04
44495841493446
2025.04
43484744452743
2025.04
34353228292132
2025.04
34454841452739
2025.04
30374936422635
2025.04
28404830463035
2025.04
26333735392331
2025.04
20284524321626
2025.04
16263528301423
2025.04
13262820191118