Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference Evaluation via Multi-Choice Queries on PrefEval Explicit
Loading...
81.3
Accuracy
MemCoE
29.716
43.108
56.5
69.892
May 1, 2026
Accuracy
Overall Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Overall Score
MemCoE
Backbone=Qwen2.5-7B-In...
2026.05
81.3
52.02
MemAgent
Backbone=Qwen2.5-7B-In...
2026.05
72.3
45
Mem-α
Backbone=Qwen3-4B, Ret...
2026.05
71.9
44.19
LightMem
Backbone=Qwen2.5-7B-In...
2026.05
64.2
41.21
A-Mem
Backbone=Qwen2.5-7B-In...
2026.05
62.3
42.64
Mem0
Backbone=Qwen2.5-7B-In...
2026.05
57.6
38.23
RAG
Backbone=Qwen2.5-7B-In...
2026.05
47.8
36.68
Long Context
Backbone=Qwen2.5-7B-In...
2026.05
31.7
26.9
Feedback
Search any
task
Search any
task