Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling on 1024-token context (val)
Loading...
28.56
Best Perplexity (PPL)
Full
28.2308
30.4529
32.675
34.8971
Jun 1, 2026
Best Perplexity (PPL)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Best Perplexity (PPL)
Full
Architecture=Full
2026.06
28.56
SWA
Architecture=SWA
2026.06
30.56
SE-Bridge
Architecture=SE-Bridge
2026.06
30.84
PBB
Architecture=PBB
2026.06
31.38
Bridge
Architecture=Bridge
2026.06
31.74
Block
Architecture=Block
2026.06
36.79
Feedback
Search any
task
Search any
task
