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

Multiple Choice Question Answering on OpenBookQA

44.4Accuracy

Original

14.86422.53230.237.868Jan 13, 2026Feb 9, 2026Mar 8, 2026Apr 5, 2026May 2, 2026May 29, 2026Jun 26, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
44.4
2026.05
42.4
2026.05
37.8
2026.05
37.8
2026.05
37.4
2026.01
36.4
2026.05
36.4
2026.01
35
2026.01
34.8
2026.01
34.4
2026.01
34.4
2026.01
34.4
2026.05
34.4
2026.01
34.2
2026.01
34.2
2026.01
34
2026.01
34
2026.01
33.6
2026.01
33.6
2026.01
33.6
2026.01
33.4
2026.01
33.2
2026.01
33
2026.01
32.6
2026.01
32.4
2026.06
27.4
2026.06
27
2026.06
25.6
2026.05
24.4
2026.06
16