Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Complex Task Solving on BrowseComp+ Compositional Stream
Loading...
90
Accuracy (1st-Q)
MEMPROBE
47.36
58.43
69.5
80.57
Jun 1, 2026
Accuracy (1st-Q)
Plasticity Gain (PG)
Accuracy (2nd-Q)
Stability Gain (SG)
Updated 1d ago
Evaluation Results
Method
Method
Links
Accuracy (1st-Q)
Plasticity Gain (PG)
Accuracy (2nd-Q)
Stability Gain (SG)
MEMPROBE
2026.06
90
40
89
-1
ExpRAG
2026.06
82
32
84
2
ReMem
2026.06
76
26
66
-10
AWM
2026.06
69
19
76
7
DC-RS
2026.06
64
14
67
3
ReAct
2026.06
50
-
50
-
LangMem
2026.06
49
-1
44
-5
Mem0
2026.06
49
-1
47
-2
Feedback
Search any
task
Search any
task