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

Multiple-choice Question Answering on BoolQ

0.887MC Accuracy

Original

0.406520.531260.6560.78074Feb 9, 2026Feb 27, 2026Mar 17, 2026Apr 4, 2026Apr 22, 2026May 10, 2026May 28, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.05
0.887
2026.05
0.885
2026.05
0.885
2026.05
0.884
2026.05
0.881
2026.05
0.874
2026.05
0.861
2026.05
0.859
2026.05
0.851
2026.02
0.8294
2026.02
0.8242
2026.05
0.818
2026.02
0.8153
2026.02
0.802
2026.02
0.8012
2026.05
0.755
2026.05
0.745
2026.05
0.74
2026.05
0.738
2026.05
0.734
2026.05
0.719
2026.05
0.704
2026.05
0.699
2026.05
0.697
2026.05
0.692
2026.05
0.678
2026.05
0.659
2026.05
0.643
2026.05
0.636
2026.05
0.635
2026.05
0.631
2026.05
0.631
2026.05
0.628
2026.05
0.619
2026.05
0.618
2026.05
0.615
2026.05
0.596
2026.05
0.589
2026.05
0.579
2026.05
0.578
2026.05
0.573
2026.05
0.534
2026.05
0.504
2026.05
0.499
2026.05
0.429
2026.05
0.425