Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context evaluation on RULER 8k context length
Loading...
83.8
Accuracy
PARTREP
72.672
75.561
78.45
81.339
Jul 2, 2026
Accuracy
Updated 23d ago
Evaluation Results
Method
Method
Links
Accuracy
PARTREP
Backbone=Qwen 2.5-3B,...
2026.07
83.8
Full Repetition
Backbone=Qwen 2.5-3B
2026.07
82.3
No Repetition
Backbone=Qwen 2.5-3B
2026.07
80
LLMLingua
Backbone=Qwen 2.5-3B
2026.07
73.1
Feedback
Search any
task
Search any
task
