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

Question Answering on ARC-E (0-shot)

87.88Accuracy

Moving Average Regularized Looping

22.224839.269956.31573.3601Sep 30, 2025Nov 2, 2025Dec 6, 2025Jan 9, 2026Feb 12, 2026Mar 18, 2026Apr 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
87.88
2026.02
87.84
2026.02
87.84
2026.02
87.84
2026.02
87.84
2026.02
82.4
2025.09
81.57
2025.09
81.36
2026.02
80.3
2026.02
80.22
2026.02
80.18
2026.02
80.01
2026.02
79.84
2025.12
79.63
2026.02
77.69
2026.02
77.61
2026.02
77.57
2026.02
77.4
2026.02
77.31
2026.02
77.1
2025.09
75.08
2025.12
74.92
2025.09
74.54
2025.12
73.99
2025.12
73.91
2026.02
73.6
2025.12
73.15
2026.02
71.6
2025.12
71.25
2025.12
63.97
2025.12
60.14
2026.04
53.58
2026.04
53
2025.12
46.25
2026.04
44.65
2026.04
42.47
2025.12
24.75