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

Long-context Question Answering on DetectiveQA-En

75.5Accuracy

MiA

49.70856.40463.169.796Dec 19, 2025Jan 11, 2026Feb 3, 2026Feb 26, 2026Mar 21, 2026Apr 13, 2026May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2025.12
75.5-
2025.12
75.5-
2025.12
75.33-
2026.05
74.744.7
2025.12
73.33-
2025.12
72.33-
2025.12
71.83-
2025.12
71.82-
2025.12
71.67-
2025.12
71.5-
2025.12
71.17-
2025.12
71.17-
2026.05
70.744.7
2026.05
70.744.7
2025.12
70.33-
2025.12
70.33-
2025.12
70-
2025.12
69.67-
2025.12
69.17-
2025.12
69-
2025.12
68.17-
2025.12
67.67-
2025.12
67.17-
2025.12
66.83-
2025.12
66.67-
2025.12
66.5-
2025.12
65.83-
2025.12
65.33-
2025.12
62.33-
2025.12
61.33-
2025.12
61.33-
2025.12
59.83-
2026.05
59.334
2026.05
58.724.7
2025.12
58-
2025.12
55.5-
2025.12
55.17-
2026.05
50.724.7