Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on RealMem
Loading...
70.1
LLM-Judge Accuracy
SEGTREEMEM
47.74
53.545
59.35
65.155
Jun 3, 2026
LLM-Judge Accuracy
Token-Level F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
LLM-Judge Accuracy
Token-Level F1
SEGTREEMEM
Variant=Best, Backbone...
2026.06
70.1
36.4
SEGTREEMEM
Variant=No-Propagation...
2026.06
65.9
35.9
A-MEM
Variant=Default, Backb...
2026.06
63.5
36.1
Dense
Variant=Default, Backb...
2026.06
63.1
36.3
HippoRAG
Variant=Default, Backb...
2026.06
62.9
35.9
RAPTOR
Variant=Default, Backb...
2026.06
61.8
36.2
BM25
Variant=Default, Backb...
2026.06
61.1
35.9
MemTree
Variant=Default, Backb...
2026.06
59.7
36
Mem0
Variant=Default, Backb...
2026.06
48.6
35.1
Feedback
Search any
task
Search any
task