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

Science Question Answering on ARC Easy (Character-level Accuracy)

87.8Accuracy (Character-level)

No pruning

24.77641.13857.573.862Mar 16, 2026Mar 17, 2026Mar 19, 2026Mar 20, 2026Mar 22, 2026Mar 23, 2026Mar 25, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.03
87.8
2026.03
80.2
2026.03
79.1
2026.03
77.9
2026.03
74.83
2026.03
74.6
2026.03
73
2026.03
72.26
2026.03
66.55
2026.03
66.04
2026.03
63.47
2026.03
63.26
2026.03
62
2026.03
61.7
2026.03
58.08
2026.03
57.32
2026.03
51.3
2026.03
49.1
2026.03
27.4
2026.03
27.2