Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context memory evaluation on LoCoMo (test)
Loading...
39.39
SingleHop F1
PPRO (Ours)
14.482
20.9485
27.415
33.8815
May 28, 2026
SingleHop F1
SingleHop B-1
Temporal F1
Temporal B-1
OpenDomain F1
OpenDomain B-1
MultiHop F1
MultiHop B-1
Overall F1
Overall B-1
Updated 23d ago
Evaluation Results
Method
Method
Links
SingleHop F1
SingleHop B-1
Temporal F1
Temporal B-1
OpenDomain F1
OpenDomain B-1
MultiHop F1
MultiHop B-1
Overall F1
Overall B-1
PPRO (Ours)
Base Model=Qwen2.5-7B,...
2026.05
39.39
29.81
52.5
43.76
24
22.25
43.34
38.08
43.2
36.68
MemAgent
Base Model=Qwen2.5-7B,...
2026.05
34.84
25.02
21.09
14.91
23.44
21.73
46.64
43.52
37.97
33.11
MEM1
Base Model=Qwen2.5-7B,...
2026.05
15.44
14.21
14.73
12.6
20.54
19.01
21.63
16.65
19.07
15.56
Feedback
Search any
task
Search any
task