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

Scientific Reasoning on AI2-ARC Scientific

79Recall

CorDA

50.71258.05665.472.744May 23, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
7980.3
2026.05
71.281.63
2026.05
71.280
2026.05
70.578.96
2026.05
70.477.53
2026.05
68.250.96
2026.05
66.879.08
2026.05
66.288.05
2026.05
6488.13
2026.05
6487.54
2026.05
63.977.82
2026.05
63.281.14
2026.05
6383.29
2026.05
6380.09
2026.05
6377.9
2026.05
62.388.8
2026.05
62.287.37
2026.05
61.787.67
2026.05
6186.03
2026.05
60.484.47
2026.05
60.384.01
2026.05
60.289.1
2026.05
6087.96
2026.05
6084.89
2026.05
59.388.43
2026.05
58.488.3
2026.05
58.479.46
2026.05
5881.52
2026.05
56.885.19
2026.05
52.779.92
2026.05
5278.54
2026.05
51.860.31