Skip to content

Listings

All listings: Novita AI

Every listing for the models on page 6 of 8 of Novita AI, including each model's other versions and routes. Back to Novita AI

Sold by Novita AI

25 listings on this page sold by Novita AI.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValue
NousResearch: Hermes 2 Pro - Llama-3 8B
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
nousresearch/hermes-2-pro-llama-3-8b
94.7
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.14$0.148KNot enough data yet
94.2
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.05$0.058KNot enough data yet
L3 8B Lunaris V1sao10k/l3-8b-lunaris
93.9
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.05$0.058KNot enough data yet
Llama 3 8B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionLlama-3.3-8B-InstructWe compared the version names in our catalogue.
93.2
From 199 benchmarks. Plenty of data behind it.
β‰ˆ 76Β Β±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.04$0.048K
46.4
Poor value (46.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Qwen2 7B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen2.5 7B InstructWe compared release dates and version names in our catalogue.
93.0
From 113 benchmarks. Plenty of data behind it.
71Β Β±9stale
Coding IQ 70.6, 95% interval 61–80. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$0.054$0.054Not published by the providerNot enough data yet
Llama 3.2 11B Vision Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
92.2
From 59 benchmarks. Plenty of data behind it.
Not enough data yet$0.06$0.06Not published by the provider
56.1
Good value (56.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
DeepSeek R1 Distill Llama 8B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
90.0
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.04$0.04Not published by the providerNot enough data yet
Llama 3.2 3B
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
meta-llama/llama-3.2-3b-instruct
86.5
From 255 benchmarks. Plenty of data behind it.
β‰ˆ 76Β Β±14
Coding IQ 75.7, 95% interval 62–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.03$0.0533K
44.3
Poor value (44.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Llama 3.2 1B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
83.4
From 93 benchmarks. Plenty of data behind it.
Not enough data yet$0.02$0.02131K
43.7
Poor value (43.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
BGE Reranker v2 M3
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.01$0.008KNot enough data yet
PaddleOCR VL
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.02$0.0216KNot enough data yet
DeepSeek-OCR
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.03$0.038KNot enough data yet
DeepSeek OCR 2
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.03$0.038KNot enough data yet
AutoGLM Phone 9B Multilingual
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.035$0.13866KNot enough data yet
llama-3.1-8b-instruct-max
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.05$0.05Not published by the providerNot enough data yet
Qwen3 Reranker 8B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.05$0.0033KNot enough data yet
Not enough data yetNot enough data yet$0.06$0.06Not published by the providerNot enough data yet
Baichuan M2 32B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.07$0.07131KNot enough data yet
MythoMax L2 13b
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.09$0.094KNot enough data yet
ERNIE 4.5 VL 28B A3B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.14$0.5630K
39.7
Poor value (39.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Nous-Hermes-Llama2-13b
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.17$0.17Not published by the providerNot enough data yet
Not enough data yetNot enough data yet$0.20$0.60262KNot enough data yet
Macaron V1 Tall
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.2475cache read $0.044$1.43262KNot enough data yet
qwen3-omni-30b-a3b-instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.25$0.9766KNot enough data yet
Qwen3 Omni 30B A3B Thinking
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.25$0.9766KNot enough data yet

Run by Novita AI

8 listings on this page where Novita AI runs the model. Another provider sells these listings.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValue
NousResearch: Hermes 2 Pro - Llama-3 8B
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
NousResearch/Hermes-2-Pro-Llama-3-8B
Β Hugging Face
94.7
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.14$0.148KNot enough data yet
Β Hugging Face
94.2
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.05$0.058KNot enough data yet
Β Requesty
94.2
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.05$0.058KNot enough data yet
Β Hugging Face
93.9
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.05$0.058KNot enough data yet
Llama 3 8B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionLlama-3.3-8B-InstructWe compared the version names in our catalogue.
meta-llama/Meta-Llama-3-8B-Instruct
Β Hugging Face
93.2
From 199 benchmarks. Plenty of data behind it.
β‰ˆ 76Β Β±11
Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.04$0.048K
46.4
Poor value (46.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
AutoGLM Phone 9B Multilingual
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Β Hugging FaceNot enough data yetNot enough data yet$0.035$0.13866KNot enough data yet
Baichuan M2 32B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Β RequestyNot enough data yetNot enough data yet$0.07$0.07131KNot enough data yet
MythoMax L2 13b
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Β RequestyNot enough data yetNot enough data yet$0.09$0.094KNot enough data yet

How this data works