Skip to main content
c-metrics
Projects
model-latency-benchmarking
Objects
model_generation_latency
Id9BwLoYZKApbYpQflKu0ytd3sqWnargbqd1Jphjy8k
Log in
Sign up
Project
Traces
Evals
Playground
Monitors
Leaders
Threads
Assets
Assets
All assets
Prompts
Ops
Models
Datasets
Scorers
model_generation_latency:v15
Name
model_generation_latency
(16 versions)
Last updated
10 months ago
Storage size
913B (14.6kB from all versions)
Leaderboard
Values
Use
Calls
Dataset:v2
TimingScorer:v6
Summary
1
Model
2
avg_token_per_sec
3
avg_token_count
4
avg_gen_timing
5
total_tokens
6
Avg. Latency
7
Run Date
8
Trials
9
BaselineHF:v34
1060.23
4156.50
3.92
83130.00
3.92
10 months ago
1.00
BaselineHF:v36
2129.77
4156.45
1.95
83129.00
1.95
10 months ago
1.00
BaselineHF:v18
183.95
4140.35
22.51
82807.00
22.53
10 months ago
1.00
BaselineHF:v28
N/A
N/A
N/A
N/A
N/A
10 months ago
1.00
BaselineHF:v17
147.15
4174.60
28.37
83492.00
28.39
10 months ago
1.00
BaselineHF:v32
1072.67
4156.50
3.87
83130.00
3.88
10 months ago
1.00
BaselineHF:v19
N/A
N/A
N/A
N/A
N/A
10 months ago
1.00
BaselineHF:v30
1293.18
4123.30
3.19
82466.00
3.19
10 months ago
1.00
BaselineHF:v16
321.62
4174.60
12.98
83492.00
13.00
10 months ago
1.00
BaselineHF:v35
1208.20
4123.30
3.41
82466.00
3.41
10 months ago
1.00
BaselineHF:v31
1271.39
4123.30
3.24
82466.00
3.24
10 months ago
1.00
BaselineHF:v33
1028.52
4156.50
4.04
83130.00
4.04
10 months ago
1.00