ResearchBenchmarksLong-context Memory Evaluation on LongMemEval-S (seed 101)Follow0.01DeltaRegimes0.0090.00950.010.0105Jun 8, 2026Evaluation ResultsMethodMethodLinksDeltaW->R CountR->W CountDiscordant CountConfirmation Rate (Base)Confirmation Rate (Post-hoc)OPT Score (Base)McNemar p-value (Post-hoc)Regimespromotes (total)=6promotes (total)=62026.060.0176137879881