Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Inference Efficiency on WQ
Loading...
0.014
Relative Execution Time Overhead
Perplexity
-0.06296
0.45652
0.976
1.49548
Mar 20, 2026
Relative Execution Time Overhead
Updated 26d ago
Evaluation Results
Method
Method
Links
Relative Execution Time Overhead
Perplexity
Model=Llama-3-8B
2026.03
0.014
Perplexity
Model=Llama-2-7B
2026.03
0.015
Perplexity
Model=Mistral-7B
2026.03
0.017
Perplexity
Model=Qwen2.5-3B
2026.03
0.029
Perplexity
Model=Qwen2.5-7B
2026.03
0.031
Perplexity
Model=Qwen2.5-14B
2026.03
0.041
STC
Model=Llama-2-7B
2026.03
0.473
STC
Model=Mistral-7B
2026.03
0.966
STC
Model=Qwen2.5-14B
2026.03
1.352
STC
Model=Llama-3-8B
2026.03
1.577
STC
Model=Qwen2.5-7B
2026.03
1.9
STC
Model=Qwen2.5-3B
2026.03
1.938
Feedback
Search any
task
Search any
task