Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Inference on WildChat
Loading...
75.17
RPS (Requests/s)
v1
1.2988
20.4769
39.655
58.8331
May 30, 2026
RPS (Requests/s)
TTFT (ms)
TPOT (ms)
Percentage Difference
Updated 1d ago
Evaluation Results
Method
Method
Links
RPS (Requests/s)
TTFT (ms)
TPOT (ms)
Percentage Difference
v1
GPU=H200, Model=Gemma-...
2026.05
75.17
-
-
-
EB(k^*)
GPU=H200, Model=Gemma-...
2026.05
74.05
-
-
-1.5
v0
GPU=H200, Model=Gemma-...
2026.05
71.82
-
-
-
EB(k^*)
GPU=RTX PRO 6000, Mode...
2026.05
56.26
-
-
5.4
v0
GPU=RTX PRO 6000, Mode...
2026.05
55.97
-
-
-
v1
GPU=RTX PRO 6000, Mode...
2026.05
53.36
-
-
-
EB(k*)
GPU=B300
2026.05
52.34
2.87
22.12
-
v1
GPU=B300
2026.05
50.47
2.08
24
-
EB(k*)
GPU=L40S
2026.05
14.7
92.16
138.16
-
v1
GPU=L40S
2026.05
10.36
132.47
189.7
-
v0
GPU=L40S
2026.05
4.14
157.21
171.02
-
Feedback
Search any
task
Search any
task