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

Common Sense Reasoning on NoRa Irrelevant Rationales

60Accuracy

SC

4.04818.57433.147.626Oct 31, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.10
60
2024.10
57.7
2024.10
55.7
2024.10
54.7
2024.10
53.2
2024.10
50.2
2024.10
49.7
2024.10
46.7
2024.10
46
2024.10
45.6
2024.10
45
2024.10
44.7
2024.10
43.6
2024.10
42.7
2024.10
42.3
2024.10
41.9
2024.10
40.8
2024.10
40.3
2024.10
40.3
2024.10
40.2
2024.10
39.7
2024.10
39.3
2024.10
37.8
2024.10
37.7
2024.10
37
2024.10
36.2
2024.10
36.1
2024.10
36
2024.10
35.7
2024.10
35.5
2024.10
34.9
2024.10
33.4
2024.10
33.3
2024.10
31.1
2024.10
29.9
2024.10
28.3
2024.10
28.3
2024.10
11
2024.10
10.5
2024.10
6.2