Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on LongBookQA-zh (test)
Loading...
39.44
F1
MemSearch-o1
21.4688
26.1344
30.8
35.4656
Apr 19, 2026
F1
EM
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1
EM
MemSearch-o1
2026.04
39.44
33.86
Direct RAG
2026.04
37.28
30.16
A-Mem
2026.04
28.64
23.81
Amber
2026.04
27.54
21.69
Search-o1 (Refined)
Refined=true
2026.04
22.16
18.52
Feedback
Search any
task
Search any
task