Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prompt Compression on 16K-token input
Loading...
0.3
Compression Latency (s)
LLMLingua-2
-0.448
4.601
9.65
14.699
Mar 13, 2026
Compression Latency (s)
Attention Preservation Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Compression Latency (s)
Attention Preservation Score
LLMLingua-2
Requires Neural Inf.=X...
2026.03
0.3
-
RECOMP
Requires Neural Inf.=T...
2026.03
0.5
-
Selective Context
Requires Neural Inf.=G...
2026.03
1
-
LLMLingua
Requires Neural Inf.=L...
2026.03
2
-
vLLM Semantic Router
Requires Neural Inf.=N...
2026.03
19
-
Feedback
Search any
task
Search any
task