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

Question Answering on ARC Challenge (Accuracy)

87.3Accuracy (ARC)

Frozen LLM graph

58.07665.66373.2580.837Oct 26, 2025Nov 30, 2025Jan 4, 2026Feb 9, 2026Mar 16, 2026Apr 20, 2026May 26, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
87.3
2026.04
83.45
2026.04
82.85
2026.04
82.68
2026.04
82.42
2026.04
82.34
2026.04
82.34
2026.04
82.29
2026.04
82.08
2026.04
82
2026.04
82
2026.04
81.91
2026.04
81.91
2026.04
81.83
2026.04
81.83
2026.04
81.74
2026.05
81.6
2026.04
81.57
2026.04
81.4
2026.04
81.4
2026.05
81.4
2026.04
81.31
2026.04
81.23
2026.04
81.23
2026.04
81.06
2026.05
81
2026.04
80.89
2026.04
80.8
2026.05
80.8
2026.05
80.71
2026.04
80.63
2026.04
80.63
2026.04
80.55
2026.05
79.86
2026.05
79.8
2026.05
79.4
2026.05
78.8
2026.05
78.6
2026.04
78.2
2026.05
77.82
2026.05
77.05
2026.05
76.96
2026.05
76.93
2026.05
76.3
2026.05
76.02
2026.04
75.9
2026.05
75.34
2026.04
75.3
2026.05
75.03
2026.05
74.11
2026.04
73.9
2026.05
73.89
2026.05
73.84
2026.05
73.12
2026.05
73.04
2026.05
72.98
2026.05
72.81
2026.05
72.8
2026.05
72.35
2026.05
69.71
2026.05
69.17
2026.05
68.14
2026.05
67.95
2026.04
67.1
2026.05
65.7
2026.05
65.1
2026.05
65
2026.05
64.88
2026.05
64.8
2026.05
64.42
2025.10
64.4
2026.05
64.1
2025.10
64.1
2026.05
64
2026.05
64
2026.05
63.28
2026.05
62.2
2026.05
61.9
2026.05
61.9
2026.05
61.9
2026.05
61.9
2026.05
61.9
2026.05
61.7
2026.05
61.4
2026.05
61.3
2026.05
61
2026.03
60.5
2026.03
60.5
2026.05
60.4
2026.04
60.3
2026.05
60.3
2026.04
60.2
2026.04
59.8
2026.04
59.6
2026.04
59.5
2026.04
59.5
2026.04
59.4
2026.04
59.3
2026.05
59.25
2026.04
59.2
Showing 100 of 598 rows