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

Question Answering on HeadQA

93.4Accuracy

DeepSeek-R1

26.569643.919861.2778.6202May 11, 2023Nov 18, 2023May 27, 2024Dec 4, 2024Jun 13, 2025Dec 21, 2025Jul 1, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.07
93.4
2026.07
91
2026.07
85.7
2026.07
84.4
2026.07
84
2026.07
83.9
2026.07
83.4
2026.07
81.5
2026.07
81.3
2026.04
80.56
2026.04
80.45
2026.04
80.38
2026.04
80.23
2026.04
80.2
2026.04
80.16
2026.04
80.05
2026.04
80.05
2026.04
80.01
2026.04
79.98
2026.04
79.94
2026.04
79.94
2026.04
79.94
2026.04
79.91
2026.04
79.87
2026.04
79.8
2026.04
79.76
2026.04
79.76
2026.04
79.69
2026.04
79.69
2026.04
79.65
2026.04
79.58
2026.04
79.5
2026.04
79.5
2026.04
79.47
2026.04
79.43
2026.04
78.01
2026.07
75.6
2026.07
73
2026.07
68.5
2026.07
67.6
2026.07
67.5
2026.04
66.59
2026.04
66.56
2026.04
66.52
2026.04
66.48
2026.04
66.45
2026.04
66.41
2026.04
66.37
2026.07
66.2
2026.04
66.19
2026.04
66.08
2026.04
66.01
2026.04
65.97
2026.04
65.9
2026.04
65.9
2026.04
65.79
2026.04
65.75
2026.04
65.68
2026.04
65.68
2026.04
65.57
2026.07
65.5
2026.04
65.43
2026.04
65.32
2026.04
65.24
2026.04
65.21
2026.04
65.1
2026.04
65.03
2026.04
64.92
2026.04
64.9
2026.04
64.77
2026.04
64.77
2026.04
64.4
2026.04
62.9
2026.04
60.3
2026.04
59.5
2026.04
58.5
2026.04
58.4
2026.04
58.1
2026.04
57.3
2026.04
56
2026.04
53.5
2026.04
51.2
2023.05
34.48
2023.05
29.14