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

Logical Reasoning on RuleBERT

67.7Accuracy

Beam Search

40.34847.44954.5561.651Apr 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
67.7
2026.04
67.7
2026.04
63.9
2026.04
63.4
2026.04
63.4
2026.04
62
2026.04
60.8
2026.04
60.3
2026.04
60.3
2026.04
59
2026.04
58.2
2026.04
57.5
2026.04
57.3
2026.04
57
2026.04
51.9
2026.04
51.9
2026.04
51.7
2026.04
51.7
2026.04
50.8
2026.04
50.7
2026.04
50.3
2026.04
50.3
2026.04
48.8
2026.04
47.4
2026.04
43.7
2026.04
43.2
2026.04
41.6
2026.04
41.4