Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-Context Retrieval on RULER 8K
Loading...
99.67
Score
Olmo3 512swa
7.8068
31.6559
55.505
79.3541
Apr 27, 2026
May 8, 2026
May 19, 2026
May 30, 2026
Jun 10, 2026
Jun 21, 2026
Jul 3, 2026
Score
Updated 18d ago
Evaluation Results
Method
Method
Links
Score
Olmo3 512swa
Tuning Protocol=Full p...
2026.07
99.67
HiLS-Attn NoPE-Q-Cal
Tuning Protocol=Full p...
2026.07
99.67
HiLS-Attn HoPE-Q-Cal
Tuning Protocol=Full p...
2026.07
99
HiLS-Attn RoPE-Q-Cal
Tuning Protocol=Full p...
2026.07
98.67
MSA-PT
Training Strategy=from...
2026.06
84.2
Full
Training Strategy=Full...
2026.06
79.8
MSA-CPT
Training Strategy=spar...
2026.06
77.2
Hybrid-GDN
setting=Train-from-scr...
2026.04
76.01
Hybrid-SCA
setting=Train-from-scr...
2026.04
75.22
Hybrid-KSA
setting=Train-from-scr...
2026.04
73.35
Full
setting=Train-from-scr...
2026.04
72.85
Hybrid-SWA
setting=Train-from-scr...
2026.04
71.69
KSA
setting=Train-from-scr...
2026.04
65.91
LMK token tuning
Tuning Protocol=Freezi...
2026.07
22.33
Olmo3 Base
Tuning Protocol=Freezi...
2026.07
11.34
Feedback
Search any
task
Search any
task