Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling on ProofPile (4K)
Loading...
3.26
Perplexity
LongAlpaca-16K
3.2272
3.4486
3.67
3.8914
Mar 5, 2026
Perplexity
Updated 1mo ago
Evaluation Results
Method
Method
Links
Perplexity
LongAlpaca-16K
Base Model=Mistral-7B,...
2026.03
3.26
SHAREDLLM
Base Model=LLaMA-2, Su...
2026.03
3.36
StreamingLLM
Base Model=LLaMA-2, Su...
2026.03
3.47
Activation Beacon
Base Model=LLaMA-2, Su...
2026.03
3.47
SHAREDLLM
Base Model=Mistral-7B,...
2026.03
3.58
LongAlpaca-16K
Base Model=LLaMA-2, Su...
2026.03
3.82
Activation Beacon
Base Model=Mistral-7B,...
2026.03
3.82
StreamingLLM
Base Model=Mistral-7B,...
2026.03
4.08
Feedback
Search any
task
Search any
task