Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Long-context Modeling Efficiency on Ruler benchmark leaderboard · SOTA2 Research

Research Benchmarks

Long-context Modeling Efficiency on Ruler

9Decoding SpeedupLAVA

Updated 4mo ago

Evaluation Results

Method	Links
LAVA2026.03		9	1	60

SOTA Paper

LAVA

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation

Dataset

RULER

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Long-context Modeling Efficiency on InfiniteBench Long-running conversation on LOCOMO (test)Long-term Conversational Memory Evaluation on LOCCO Long-context Conversational Memory on LOCCO Long-context Memory Management on LOCOMO