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

Question Answering on ARC Challenge (Zero-shot)

48.46Zero-shot Accuracy

Dense

17.135225.267633.441.5324Oct 2, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
48.46
2025.10
43.68
2025.10
43.17
2025.10
43.09
2025.10
42.66
2025.10
42.41
2025.10
41.64
2025.10
40.53
2025.10
40.44
2025.10
39.76
2025.10
38.48
2025.10
37.97
2025.10
36.95
2025.10
36.01
2025.10
34.13
2025.10
29.78
2025.10
29.61
2025.10
27.56
2025.10
27.13
2025.10
25.34
2025.10
24.32
2025.10
22.1
2025.10
21.84
2025.10
21.42
2025.10
21.33
2025.10
21.08
2025.10
20.65
2025.10
20.48
2025.10
20.05
2025.10
19.88
2025.10
19.62
2025.10
19.11
2025.10
19.03
2025.10
18.94
2025.10
18.43
2025.10
18.34