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
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value |
|---|---|---|---|---|---|---|
NousResearch: Hermes 2 Pro - Llama-3 8B πΊπΈMaker 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. | 94.7From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.14 | $0.14 | 8K | βNot enough data yet |
94.2From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.05 | $0.05 | 8K | βNot enough data yet | |
L3 8B Lunaris V1sao10k/l3-8b-lunarissao10k/l3-8b-lunaris | 93.9From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.05 | $0.05 | 8K | βNot enough data yet |
Llama 3 8B Instruct πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 93.2From 199 benchmarks. Plenty of data behind it. | β 76Β Β±11Coding IQ 75.7, 95% interval 65β87. 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 | $0.04 | 8K | 46.4Poor 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 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 93.0From 113 benchmarks. Plenty of data behind it. | 71Β Β±9staleCoding IQ 70.6, 95% interval 61β80. 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 | $0.054 | βNot published by the provider | βNot enough data yet |
Llama 3.2 11B Vision Instruct πΊπΈMaker 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. | 92.2From 59 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.06 | $0.06 | βNot published by the provider | 56.1Good 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 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 90.0From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.04 | $0.04 | βNot published by the provider | βNot enough data yet |
Llama 3.2 3B πΊπΈMaker 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. | 86.5From 255 benchmarks. Plenty of data behind it. | β 76Β Β±14Coding IQ 75.7, 95% interval 62β89. 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 | $0.05 | 33K | 44.3Poor 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 πΊπΈMaker 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. | 83.4From 93 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.02 | $0.02 | 131K | 43.7Poor 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 π¨π³Maker 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. | βNot enough data yet | βNot enough data yet | $0.01 | $0.00 | 8K | βNot enough data yet |
PaddleOCR VL π¨π³Maker 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. | βNot enough data yet | βNot enough data yet | $0.02 | $0.02 | 16K | βNot enough data yet |
DeepSeek-OCR π¨π³Maker 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. | βNot enough data yet | βNot enough data yet | $0.03 | $0.03 | 8K | βNot enough data yet |
DeepSeek OCR 2 π¨π³Maker 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. | βNot enough data yet | βNot enough data yet | $0.03 | $0.03 | 8K | βNot enough data yet |
AutoGLM Phone 9B Multilingual π¨π³Maker 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. | βNot enough data yet | βNot enough data yet | $0.035 | $0.138 | 66K | βNot enough data yet |
llama-3.1-8b-instruct-max πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.05 | $0.05 | βNot published by the provider | βNot enough data yet |
Qwen3 Reranker 8B π¨π³Maker 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. | βNot enough data yet | βNot enough data yet | $0.05 | $0.00 | 33K | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | $0.06 | $0.06 | βNot published by the provider | βNot 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. | βNot enough data yet | βNot enough data yet | $0.07 | $0.07 | 131K | βNot 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. | βNot enough data yet | βNot enough data yet | $0.09 | $0.09 | 4K | βNot enough data yet |
ERNIE 4.5 VL 28B A3B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.14 | $0.56 | 30K | 39.7Poor 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 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.17 | $0.17 | βNot published by the provider | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | $0.20 | $0.60 | 262K | βNot 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. | βNot enough data yet | βNot enough data yet | $0.2475cache read $0.044 | $1.43 | 262K | βNot enough data yet |
qwen3-omni-30b-a3b-instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.25 | $0.97 | 66K | βNot enough data yet |
Qwen3 Omni 30B A3B Thinking π¨π³Maker 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. | βNot enough data yet | βNot enough data yet | $0.25 | $0.97 | 66K | βNot 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
| Model | Provider | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value |
|---|---|---|---|---|---|---|---|
NousResearch: Hermes 2 Pro - Llama-3 8B πΊπΈMaker 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. | 94.7From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.14 | $0.14 | 8K | βNot enough data yet | |
94.2From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.05 | $0.05 | 8K | βNot enough data yet | ||
94.2From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.05 | $0.05 | 8K | βNot enough data yet | ||
93.9From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.05 | $0.05 | 8K | βNot enough data yet | ||
Llama 3 8B Instruct πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 93.2From 199 benchmarks. Plenty of data behind it. | β 76Β Β±11Coding IQ 75.7, 95% interval 65β87. 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 | $0.04 | 8K | 46.4Poor 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 π¨π³Maker 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. | βNot enough data yet | βNot enough data yet | $0.035 | $0.138 | 66K | βNot 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. | βNot enough data yet | βNot enough data yet | $0.07 | $0.07 | 131K | βNot 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. | βNot enough data yet | βNot enough data yet | $0.09 | $0.09 | 4K | βNot enough data yet |