Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context reasoning on RULER 8K context length
Loading...
98.5
NIAH Score
UltraLLaDA+BA-Att
37.1712
53.0931
69.015
84.9369
May 19, 2026
NIAH Score
AGG Score
QA Score
VT Score
AVG Score
Updated 14d ago
Evaluation Results
Method
Method
Links
NIAH Score
AGG Score
QA Score
VT Score
AVG Score
UltraLLaDA+BA-Att
Base Model=UltraLLaDA,...
2026.05
98.5
57.65
68.5
100
87.71
UltraLLaDA
Base Model=UltraLLaDA,...
2026.05
98.28
55.29
62
100
86.22
UltraLLaDA+XAtt
Base Model=UltraLLaDA,...
2026.05
86.97
36.3
62
24.2
70.5
LLaDA1.5
Base Model=LLaDA1.5, A...
2026.05
51.56
41.6
48.02
61.6
50.25
LLaDA1.5+BA-Att
Base Model=LLaDA1.5, A...
2026.05
50.28
58.23
48.1
59.4
51.85
LLaDA1.5+XAtt
Base Model=LLaDA1.5, A...
2026.05
39.53
33.21
35.5
0.4
34.93
Feedback
Search any
task
Search any
task