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

Tabular Reasoning on MultiHier (test)

70.2Pass@1

GPT-5.4-xhigh

4.88821.84438.855.756May 21, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
70.2
2026.05
69
2026.05
68.2
2026.05
67.3
2026.05
67.3
2026.05
66.7
2026.05
66.1
2026.05
65.5
2026.05
65.2
2026.05
64.9
2026.05
64.9
2026.05
64.6
2026.05
62.5
2026.05
60.7
2026.05
60.7
2026.05
58.9
2026.05
54.3
2026.05
48.5
2026.05
45.8
2026.05
44.9
2026.05
42.3
2026.05
37.8
2026.05
31.2
2026.05
27.1
2026.05
7.4