Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-session on LongMemEval S (test)
Loading...
6.61
F1 Score
HIPPOCAMPUS
1.4516
2.7908
4.13
5.4692
Feb 14, 2026
F1 Score
Accuracy
LLM-as-a-Judge Score
Updated 2d ago
Evaluation Results
Method
Method
Links
F1 Score
Accuracy
LLM-as-a-Judge Score
HIPPOCAMPUS
2026.02
6.61
19.54
2.57
MemOS
2026.02
4.94
14.66
2.31
MemoryOS
2026.02
4.3
12.7
2.19
A-mem
2026.02
3.64
10.75
2.06
MemGPT
2026.02
2.31
6.84
1.41
MemoryBank
2026.02
1.98
5.86
1.55
ReadAgent
2026.02
1.65
4.89
1.03
Feedback
Search any
task
Search any
task