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

Single-Hop Fact-based Reasoning on MAB FC-SH 262K v3 (test)

93Accuracy

Headline pipeline

3.5626.785073.22May 31, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
93
2026.05
82
2026.05
73
2026.05
61
2026.05
60
2026.05
54
2026.05
48
2026.05
7