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

Question Answering on ARC-Challenge 0-shot (test)

90.4Accuracy

MIPO

21.936839.710957.48575.2591Sep 30, 2025Oct 26, 2025Nov 22, 2025Dec 19, 2025Jan 15, 2026Feb 11, 2026Mar 10, 2026
Updated 27d ago

Evaluation Results

MethodLinks
2026.03
90.4
2026.03
90
2026.03
88.6
2026.03
88.2
2026.03
87.8
2026.03
80.13
2026.03
79.6
2026.03
79.4
2026.03
79.4
2026.03
78.67
2026.03
70.93
2026.03
70.53
2026.03
70.47
2026.03
70.33
2026.03
68.6
2026.03
65.93
2026.03
63.67
2026.03
63.6
2026.03
62.2
2025.09
55.8
2025.09
55.55
2025.12
55.03
2026.03
52.47
2025.09
49.57
2025.12
48.89
2025.09
48.89
2025.12
47.7
2025.12
46.33
2025.12
46.16
2025.12
45.73
2026.03
42.2
2026.03
39.53
2025.12
38.48
2025.12
37.03
2026.03
33.2
2025.12
30.89
2026.03
28.53
2026.03
27.13
2025.12
24.57