Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on LoCoMo (LLM-judge accuracy and token-level F1)
Loading...
54.9
LLM-judge Accuracy
SEGTREEMEM
34.62
39.885
45.15
50.415
Jun 3, 2026
LLM-judge Accuracy
Token F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
LLM-judge Accuracy
Token F1
SEGTREEMEM
Variant=Best, Backbone...
2026.06
54.9
16.8
SEGTREEMEM
Variant=No-Propagation...
2026.06
52.5
16.1
RAPTOR
Variant=Default, Backb...
2026.06
51.8
14.6
A-MEM
Variant=Default, Backb...
2026.06
49.6
15.5
Dense
Variant=Default, Backb...
2026.06
47.7
15.3
HippoRAG
Variant=Default, Backb...
2026.06
47
15.1
BM25
Variant=Default, Backb...
2026.06
46.9
15.7
MemTree
Variant=Default, Backb...
2026.06
36.9
11.8
Mem0
Variant=Default, Backb...
2026.06
35.4
12.8
Feedback
Search any
task
Search any
task