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

Memory on RULER HotpotQA

67Score

DARE + TIES

58.6860.846365.16Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
67--
2026.06
65--
2026.06
65--
2026.06
65--
2026.06
65--
2026.06
64--
2026.06
64--
2026.06
64--
2026.06
64--
2026.06
64--
2026.06
64--
2026.06
63--
2026.06
63--
2026.06
62--
2026.06
62--
2026.06
61--
2026.06
61--
2026.06
61--
2026.06
61--
2026.06
60--
2026.06
60--
2026.06
60--
2026.06
60--
2026.06
59--
2026.01
-60.9450
2026.01
-58.5956.25
2026.01
-58.5948.44
2026.01
-78.9178.12
2026.01
-69.5368.75
2026.01
-60.0649.22
2026.01
-71.8882.03
2026.01
-76.5676.56
2026.01
-7577.34
2026.01
-75.7875
2026.01
-79.6978.13
2026.01
-78.1278.91
2026.01
-76.5676.56
2026.01
-75.7875
2026.01
-79.6978.13