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

Table Reasoning on TableBench

72.52Pass@1

ReAct

9.267225.688642.1158.5314Sep 29, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
72.5281.68
2025.09
71.0380.15
2025.09
70.9581.81
2025.09
69.9378.37
2025.09
68.9679.52
2025.09
67.679.39
2025.09
65.4476.21
2025.09
64.9775.06
2025.09
61.1172.26
2025.09
57.7975.19
2025.09
56.9669.97
2025.09
56.3663.61
2025.09
55.4770.36
2025.09
50.3858.91
2025.09
46.4476.08
2025.09
41.9852.67
2025.09
41.2251.02
2025.09
41.0170.36
2025.09
40.8450.64
2025.09
39.9550.25
2025.09
11.728.63