Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context evaluation on RULER 16k context length
Loading...
73.2
Accuracy
PARTREP
63.112
65.731
68.35
70.969
Jul 2, 2026
Accuracy
Updated 23d ago
Evaluation Results
Method
Method
Links
Accuracy
PARTREP
Backbone=Qwen 2.5-3B,...
2026.07
73.2
No Repetition
Backbone=Qwen 2.5-3B
2026.07
72.3
Full Repetition
Backbone=Qwen 2.5-3B
2026.07
72.3
LLMLingua
Backbone=Qwen 2.5-3B
2026.07
63.5
Feedback
Search any
task
Search any
task
