Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-horizon Memory Question Answering on ATM-Bench subset431
Loading...
69.61
EM
Graph-NoReader
65.9908
66.9304
67.87
68.8096
Apr 10, 2026
EM
Avg Evidence Tokens
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM
Avg Evidence Tokens
Graph-NoReader
Protocol=shared answer...
2026.04
69.61
3,672.11
Vanilla RAG
Protocol=shared answer...
2026.04
68.21
2,962.01
S3Mem
Protocol=shared answer...
2026.04
66.13
751.09
Feedback
Search any
task
Search any
task