Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-objective search on Multi-objective search memory 8-objective
Loading...
25.12
F1 Score
TMEM
17.6008
19.5529
21.505
23.4571
Jun 3, 2026
F1 Score
Exact Match (EM)
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
Exact Match (EM)
TMEM
Model=Qwen3-8B
2026.06
25.12
15.03
TMEM
Model=Qwen3-4B
2026.06
24.51
15.03
AMEM
Model=Qwen3-8B
2026.06
23.45
14.12
MemAgent/MEM1
Model=Qwen3-8B
2026.06
22.87
13.42
AMEM
Model=Qwen3-4B
2026.06
22.65
13.87
MemAgent/MEM1
Model=Qwen3-4B
2026.06
22.18
13.36
No Memory
Model=Qwen3-4B
2026.06
18.22
9.28
No Memory
Model=Qwen3-8B
2026.06
17.89
9.12
Feedback
Search any
task
Search any
task