Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

General Reasoning on BIG-Bench Hard (val)

43.46Accuracy

TAIA

11.771219.998128.22536.4519May 30, 2024
Updated 3d ago

Evaluation Results

MethodLinks
2024.05
43.46
2024.05
42.54
2024.05
37.35
2024.05
36.09
2024.05
35.85
2024.05
35.05
2024.05
33.19
2024.05
32.64
2024.05
32.54
2024.05
31.47
2024.05
31.3
2024.05
30.96
2024.05
30.93
2024.05
30.76
2024.05
30.2
2024.05
30.03
2024.05
29.58
2024.05
29.1
2024.05
28.8
2024.05
28.63
2024.05
27.71
2024.05
26.36
2024.05
26
2024.05
24.07
2024.05
23.67
2024.05
23.24
2024.05
22.5
2024.05
22.49
2024.05
22.24
2024.05
21.93
2024.05
20.21
2024.05
19.09
2024.05
18.86
2024.05
16.8
2024.05
13.9
2024.05
12.99