Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Serving on Alpaca (Average Latency)
Loading...
111.46
Average Latency (ms/token)
Oracle SJF
77.4172
307.2061
536.995
766.7839
Sep 25, 2025
Average Latency (ms/token)
Updated 26d ago
Evaluation Results
Method
Method
Links
Average Latency (ms/token)
Oracle SJF
Model=Llama
2025.09
111.46
PARS
Model=Llama
2025.09
124.92
Oracle SJF
Model=DeepSeek-R1
2025.09
137.32
Cross-Model PARS
Model=Llama
2025.09
138.53
PARS
Model=DeepSeek-R1
2025.09
148.97
Pointwise SJF
Model=Llama
2025.09
152.3
Listwise SJF
Model=Llama
2025.09
157.07
Cross-Model PARS
Model=DeepSeek-R1
2025.09
178.07
Listwise SJF
Model=DeepSeek-R1
2025.09
187.41
Pointwise SJF
Model=DeepSeek-R1
2025.09
283.39
FCFS
Model=DeepSeek-R1
2025.09
372.03
FCFS
Model=Llama
2025.09
962.53
Feedback
Search any
task
Search any
task