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

Accuracy on ARC-C (Question Answering)

86Accuracy (ARC-C)

ExpGraph

17.131235.010652.8970.7694Oct 29, 2025Dec 8, 2025Jan 17, 2026Feb 26, 2026Apr 7, 2026May 17, 2026Jun 27, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.05
86
2026.05
84.34
2026.05
83.33
2026.05
83.08
2026.05
82.58
2026.05
82.32
2026.05
82
2026.05
81.57
2026.05
81.57
2026.05
81.31
2026.05
74
2026.05
72.47
2026.05
71.72
2026.05
71.46
2026.05
70.2
2026.05
67.93
2026.05
67.42
2026.05
66.67
2026.05
65
2025.10
63.65
2026.06
63.5
2026.05
62.63
2025.10
60.92
2025.10
60.92
2026.06
59.8
2026.06
56.9
2025.10
55.72
2025.10
55.46
2025.10
54.44
2026.06
53.5
2025.10
52.47
2026.06
51.6
2026.05
51.52
2026.06
51.5
2026.06
47.5
2026.05
44.7
2025.10
41.98
2025.10
39.25
2026.06
37.4
2026.06
36
2026.06
35.8
2026.06
34.4
2026.06
33.6
2026.06
33.6
2025.11
32.85
2025.11
32.59
2025.11
32.51
2025.11
32.25
2025.11
32.24
2026.06
31.6
2026.06
31
2026.06
28.4
2025.11
27.82
2026.05
27.5
2026.06
27.2
2026.05
27.13
2026.05
26.79
2026.05
26.71
2026.06
26.4
2026.05
24.74
2026.05
24.49
2026.05
23.29
2026.05
23.21
2026.06
22.29
2026.06
22.06
2026.06
21.59
2026.06
19.78