Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context language modeling on RULER (32K Context)
Loading...
100
S-NIAH Component 1 Score
RDKV
99.792
99.846
99.9
99.954
May 8, 2026
S-NIAH Component 1 Score
S-NIAH Component 2 Score
S-NIAH Component 3 Score
MK-NIAH Component 1 Score
MK-NIAH Component 2 Score
MK-NIAH Component 3 Score
MQ-NIAH Score
MV-NIAH Score
VT Score
CWE Score
FWE Score
Average Score
Updated 22d ago
Evaluation Results
Method
Method
Links
S-NIAH Component 1 Score
S-NIAH Component 2 Score
S-NIAH Component 3 Score
MK-NIAH Component 1 Score
MK-NIAH Component 2 Score
MK-NIAH Component 3 Score
MQ-NIAH Score
MV-NIAH Score
VT Score
CWE Score
FWE Score
Average Score
RDKV
Backbone=LLaMA-3.1-8B-...
2026.05
100
98.4
99.6
98.4
98.8
71.2
99.2
98.3
98.7
37.3
71.2
88.3
HqeKV
Backbone=LLaMA-3.1-8B-...
2026.05
99.8
99.2
88.8
96.6
98.6
85.2
93.8
91
95.3
15.3
87.2
86.4
Feedback
Search any
task
Search any
task
