Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Memory Evaluation on LongMemEval-S (Seed 7, Run 3)
Loading...
0.08
Delta
Regimes
0.076
0.078
0.08
0.082
Jun 8, 2026
Delta
Write-to-Read Score
Read-to-Write Score
Discordant Count
Confirmation Accuracy (Base)
Confirmation Accuracy (Post)
Optimization Score (Base)
McNemar p-value (Post-hoc)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Delta
Write-to-Read Score
Read-to-Write Score
Discordant Count
Confirmation Accuracy (Base)
Confirmation Accuracy (Post)
Optimization Score (Base)
McNemar p-value (Post-hoc)
Regimes
promotes (total)=1
2026.06
0.08
10
2
12
74
82
80
0.039
Feedback
Search any
task
Search any
task