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

Long-term dialogue memory on LongMemEval (test)

85.75Accuracy

MemBuilder

11.96231.118550.27569.4315Jan 9, 2026Jan 13, 2026Jan 18, 2026Jan 23, 2026Jan 27, 2026Feb 1, 2026Feb 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
85.75-
2026.01
85.5-
2026.01
84.25-
2026.01
78.5-
2026.01
76-
2026.02
75.10.016
2026.01
73.25-
2026.02
730.0009
2026.02
71.2-
2026.01
69-
2026.01
66.75-
2026.02
63.60.0012
2026.01
62.75-
2026.02
62.40
2026.02
610.001
2026.01
56-
2026.01
47-
2026.02
14.8-