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

Long-context Memory Retrieval and Reasoning on WebWalker 128K

27.44F1 Score

MemSifter

21.4623.012524.56526.1175Mar 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
27.44
2026.03
26.13
2026.03
26.11
2026.03
25.8
2026.03
25.72
2026.03
25.25
2026.03
25.16
2026.03
25.01
2026.03
24.51
2026.03
24.39
2026.03
24.24
2026.03
24.19
2026.03
24.19
2026.03
24.14
2026.03
23.46
2026.03
22.79
2026.03
22.61
2026.03
22.49
2026.03
21.88
2026.03
21.69