Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Evaluation on RULER 32k context Average 13 tasks
Loading...
0.635
Score
Vanilla
0.609
0.61575
0.6225
0.62925
May 13, 2026
Score
Relative Change (%)
Average Gate Density (%)
Updated 19d ago
Evaluation Results
Method
Method
Links
Score
Relative Change (%)
Average Gate Density (%)
Vanilla
Attention Mechanism=Fu...
2026.05
0.635
-
-
Self-Pruned KV
Attention Mechanism=Se...
2026.05
0.61
-3.9
17.5
Feedback
Search any
task
Search any
task
