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

Commonsense Question Answering on CSQA (Acc, Uintra, Uinter, Usys)

98.9Accuracy

Clean (no attack)

12.78835.14457.579.856Feb 6, 2026Mar 3, 2026Mar 28, 2026Apr 22, 2026May 17, 2026Jun 11, 2026Jul 7, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.07
98.9---
2026.07
98.6---
2026.02
85.10.0980.0720.108
2026.07
78.9---
2026.02
76.40.1480.1120.162
2026.02
73.90.2150.1680.235
2026.07
73.5---
2026.02
69.50.2050.1620.275
2026.06
66.1---
2026.06
65.9---
2026.06
65---
2026.06
64.3---
2026.06
64.3---
2026.06
63.3---
2026.02
63.20.310.2050.338
2026.06
63.2---
2026.02
59.80.2580.2150.355
2026.02
580.2150.1720.288
2026.02
56.90.2750.2280.378
2026.02
51.60.3350.2750.442
2026.02
48.60.3180.2780.438
2026.02
44.80.3420.2950.472
2026.06
37.4---
2026.02
29.70.5120.5520.573
2026.06
28---
2026.07
16.1---