Try every model of Prem

Models status

Anthropic
claude-3-sonnet
100% 37.27
90 days ago Today
claude-3-haiku
100% 72.85
90 days ago Today
claude-3.5-sonnet
100% 34.11
90 days ago Today
claude-3.5-haiku
98% 32.29
90 days ago Today
claude-3.5-sonnet-v2
98% 27.66
90 days ago Today
claude-3-opus
99% 18.61
90 days ago Today
Deepseek
deepseek-r1-distill-llama-70b
100% 188.67
90 days ago Today
deepseek-r1
100% 29.77
90 days ago Today
Gpt
gpt-4o-mini
100% 56.16
90 days ago Today
gpt-4o-mini-eu
100% 99.29
90 days ago Today
gpt-4-turbo
100% 33.80
90 days ago Today
gpt-4-eu
100% 26.68
90 days ago Today
gpt-4o
100% 53.37
90 days ago Today
gpt-4o-eu
100% 87.31
90 days ago Today
Llama
llama-3-70b
100% 222.30
90 days ago Today
llama-3-8b
100% 434.27
90 days ago Today
llama-3.2-1b
100% 564.15
90 days ago Today
llama-3.1-8b
100% 367.42
90 days ago Today
llama-3.2-3b
100% 482.64
90 days ago Today
llama-3.3-70b
98% 173.61
90 days ago Today
llama-3-8b-guard
100% 8.42
90 days ago Today
Mistral
mixtral-8x7b
100% 328.66
90 days ago Today

Models performances

Group
Name
AVG Uptime
AVG t/s
Summarization
Tool use
Hallucination
DeepSeek
deepseek-r1
100%
45.89 t/s
-
Not supported
-
Anthropic
claude-3.5-haiku
100%
28.41 t/s
63%
70%
5%
Anthropic
claude-3.5-sonnet
100%
31.86 t/s
67%
60%
0%
Anthropic
claude-3.5-sonnet-v2
100%
30.88 t/s
68%
60%
5%
Anthropic
claude-3-haiku
100%
68.06 t/s
70%
70%
5%
Anthropic
claude-3-opus
100%
19.58 t/s
76%
65%
0%
Anthropic
claude-3-sonnet
100%
23.91 t/s
67%
70%
5%
gpt
gpt-4-eu
100%
26.53 t/s
59%
72%
15%
gpt
gpt-4o
100%
45.32 t/s
71%
67%
10%
gpt
gpt-4o-eu
100%
92.45 t/s
73%
83%
0%
gpt
gpt-4o-mini
100%
48.75 t/s
74%
83%
5%
gpt
gpt-4o-mini-eu
100%
101.63 t/s
72%
78%
5%
gpt
gpt-4-turbo
100%
22.77 t/s
73%
72%
5%
DeepSeek
deepseek-r1-distill-llama-70b
100%
186.30 t/s
-
Not supported
-
llama
llama-3.1-8b
100%
260.91 t/s
62%
88%
10%
llama
llama-3.2-1b
100%
551.67 t/s
45%
Not supported
20%
llama
llama-3.2-3b
100%
433.90 t/s
57%
Not supported
15%
llama
llama-3.3-70b
100%
193.66 t/s
68%
100%
0%
llama
llama-3-70b
100%
213.14 t/s
66%
85%
5%
llama
llama-3-8b
100%
266.50 t/s
64%
89%
5%
llama
llama-3-8b-guard
100%
6.74 t/s
0%
Not supported
100%
mistral
mixtral-8x7b
100%
277.85 t/s
67%
88%
10%
llama
prem-llama-3.1-8b
100%
64.72 t/s
-
Not supported
-
llama
prem-llama-3.2-1b
100%
112.36 t/s
-
Not supported
-
llama
prem-llama-3.2-3b
100%
81.99 t/s
-
Not supported
-