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

Question Answering on ARC

94.6Accuracy

Yi-34B + RTD

62.682470.968779.25587.5413May 31, 2024Sep 16, 2024Jan 2, 2025Apr 20, 2025Aug 6, 2025Nov 22, 2025Mar 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.09
94.6
2024.09
94
2024.09
93.3
2026.01
93.1
2026.01
92.3
2024.09
91.7
2024.09
91.6
2026.01
90.9
2024.09
90.7
2026.01
90.5
2026.01
90.2
2026.01
89.5
2026.01
89.3
2026.01
89.1
2026.03
88.5
2026.01
88.2
2026.01
87.5
2026.01
87.4
2024.09
87.3
2026.01
87.3
2024.09
87.1
2026.01
87
2026.01
86.7
2026.01
86.7
2026.01
86.6
2026.01
86.5
2026.01
86.4
2026.03
86.2
2024.09
86.1
2026.01
85.7
2026.01
85.1
2026.01
85.1
2026.03
85.1
2026.01
84.9
2026.03
84.8
2026.01
84
2026.01
84
2024.09
83.7
2026.01
82.6
2026.01
82.4
2026.01
82.2
2025.01
82
2025.01
82
2026.01
81.7
2026.03
81.4
2026.03
81.3
2025.01
81
2025.01
81
2025.01
81
2026.03
80.2
2026.03
79.9
2025.01
78
2024.09
76.5
2026.03
76.2
2025.01
76
2024.09
75.3
2026.03
75.3
2026.03
75.3
2024.09
75
2026.03
73.1
2026.03
71.4
2024.09
71.2
2025.01
71
2025.01
71
2025.12
69.65
2026.03
69.4
2025.12
69.28
2026.03
69.2
2025.12
68.81
2026.03
68.8
2025.12
68.69
2026.03
68.5
2025.12
67.68
2024.09
67.4
2024.09
67.3
2026.03
67.3
2025.12
67.09
2025.12
66.84
2024.05
66.81
2025.12
66.75
2025.12
66.62
2024.05
66.54
2025.12
66.46
2025.12
66.33
2025.12
66.33
2025.12
66.16
2025.12
65.99
2024.09
65
2025.01
65
2025.01
65
2026.03
65
2024.05
64.88
2025.12
64.85
2025.12
64.85
2025.12
64.59
2026.03
64.5
2024.05
64.33
2025.12
64.33
2025.12
63.99
2025.12
63.91
Showing 100 of 230 rows