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

Multiple Choice Questions on ARC Challenge

99.4Accuracy

BERT-Judge

48.23261.51674.888.084Mar 22, 2026Mar 25, 2026Mar 28, 2026Mar 31, 2026Apr 3, 2026Apr 6, 2026Apr 10, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.04
99.4--
2026.03
96.197.696.8
2026.03
9698.397.2
2026.03
95.597.495.8
2026.03
95.398.197
2026.03
9597.596.2
2026.03
94.697.295.9
2026.03
94.597.295.7
2026.03
94.595.895.1
2026.03
93.996.896
2026.03
92.295.493.5
2026.03
91.294.992.6
2026.03
90.594.792.4
2026.03
90.19189.8
2026.03
89.994.191.8
2026.03
89.392.992.6
2026.03
8992.191.5
2026.04
89--
2026.03
80.49083.6
2026.03
79.18379
2026.03
74.47168.3
2026.03
73.38378.8
2026.03
7382.578.9
2026.04
50.2--