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

Financial Question Answering on TATQA 1.0 (test)

89.99Accuracy

Program-of-Thoughts (PoT)

-0.105223.284946.67570.0651Feb 17, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.02
89.99
2024.02
88.67
2024.02
86.91
2024.02
82.11
2024.02
81.51
2024.02
79.73
2024.02
77.57
2024.02
62.93
2024.02
61.6
2024.02
59.14
2024.02
57.94
2024.02
56.25
2024.02
56.06
2024.02
55.81
2024.02
47.46
2024.02
44.66
2024.02
40.95
2024.02
35.95
2024.02
34.16
2024.02
31.38
2024.02
28.53
2024.02
25.93
2024.02
22.89
2024.02
19.11
2024.02
16.53
2024.02
10.92
2024.02
10.02
2024.02
7.24
2024.02
4.37
2024.02
3.36