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

Long-horizon Question Answering on LongMemEval-RR

46.33F1 Score

MemAgent-7B

1.786813.350924.91536.4791Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
46.33--
2026.06
45.4110061.52
2026.06
44.9999.9883.67
2026.06
36.4510060.82
2026.06
30.1732.1531.12
2026.06
27.6829.6629.15
2026.06
17.6512.469.97
2026.06
17.6326.5717.54
2026.06
15.6517.1414.64
2026.06
15.3821.417.63
2026.06
13.11--
2026.06
12.0520.2114.23
2026.06
11.56--
2026.06
8.2715.219.43
2026.06
4.987.536.15
2026.06
3.56.124.25