Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context reasoning on RULER 16K context length
Loading...
94.62
NIAH
UltraLLaDA+BA-Att
5.1176
28.3538
51.59
74.8262
May 19, 2026
NIAH
AGG
QA
VT
AVG
Updated 13d ago
Evaluation Results
Method
Method
Links
NIAH
AGG
QA
VT
AVG
UltraLLaDA+BA-Att
Base Model=UltraLLaDA,...
2026.05
94.62
44.89
53
99.4
80.93
UltraLLaDA
Base Model=UltraLLaDA,...
2026.05
93
43.12
39.5
98.4
77.51
UltraLLaDA+XAtt
Base Model=UltraLLaDA,...
2026.05
75.09
35.37
40
7.4
58.38
LLaDA1.5+BA-Att
Base Model=LLaDA1.5, A...
2026.05
16.5
18.06
74
30
26.62
LLaDA1.5+XAtt
Base Model=LLaDA1.5, A...
2026.05
15.16
15.89
37
0.6
17.51
LLaDA1.5
Base Model=LLaDA1.5, A...
2026.05
8.56
11.19
46.5
20.6
15.73
Feedback
Search any
task
Search any
task