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

Commonsense Reasoning on StrategyQA (Clean Error and ASR)

32.2Clean Error

No trust

32.0233.23534.4535.665Jun 3, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.06
32.2-
2025.06
34.3-
2025.06
34.8-
2025.06
34.9-
2025.06
36.2-
2025.06
36.7-
2025.06
-90.3
2025.06
-20.8
2025.06
-90.1
2025.06
-18.7
2025.06
-80.5
2025.06
-21.7