Listings
All listings: NanoGPT
Every listing for the models on page 11 of 40 of NanoGPT, including each model's other versions and routes. Back to NanoGPT
Sold by NanoGPT
43 listings on this page sold by NanoGPT.
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
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|
Phi 4 Multimodal 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. | 103.4From 48 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.07cache read $0.035 | $0.11 | 128K | 59.1Good value (59.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured |
L3.3 Ms Nevoria 70b Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 102.7From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.493cache read $0.2465 | $0.493 | 33K | βNot enough data yet | βNot measured |
Qwen2 72B Dracarys Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 102.3From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.493cache read $0.2465 | $0.493 | 33K | βNot enough data yet | βNot measured |
Veo 3.1 Fast πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | β 102From 10 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
Veo 3.1 Fast πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | β 102From 10 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
Magnum V2 72B Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 101.2From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $2.006cache read $1.003 | $2.992 | 16K | βNot enough data yet | βNot measured |
Text Embedding 3 Small πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 101.2From 117 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.02 | β | 8K | βNot enough data yet | βNot measured |
Text Embedding Ada 002 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 101.1From 38 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.10 | β | 8K | βNot enough data yet | βNot measured |
FLUX.2 [flex] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 101.0From 151 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
FLUX.2 [flex] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 101.0From 151 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
BGE 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. | 100.9From 136 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.01 | β | 8K | βNot enough data yet | βNot measured |
Ministral 3B π«π·Maker headquartered in FR, 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. | 100.6From 24 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.10cache read $0.01 | $0.10 | 131K | 38.6Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured |
Ministral 3B Inference by Kitaniπ«π·Maker headquartered in FR, 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. | 100.6From 24 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.0945cache read $0.0473 | $0.0945 | βNot published by the provider | 38.6Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured |
FLUX.2 [max] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 100.5From 170 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
FLUX.2 [max] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 100.5From 170 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
Llama 3.1 Nemotron 70B Instruct HF 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. | 100.2From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.357cache read $0.1785 | $0.408 | 16K | βNot enough data yet | βNot measured |
GPT Image 1 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 45 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
FLUX.2 [pro] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 99.9From 155 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
FLUX.2 [pro] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 99.9From 155 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
Doubao Seedream 4.5 Newer version | 98.2From 177 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
Doubao Seedream 4.5 Newer version | 98.2From 177 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
Mistral Nemo π«π·Maker headquartered in FR, 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. | 98.1From 85 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.1003cache read $0.0502 | $0.1207 | 16K | 52.2Fair value (52.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 113.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Nemo Inference by Kitaniπ«π·Maker headquartered in FR, 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. | 98.1From 85 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.0948cache read $0.0474 | $0.1141 | βNot published by the provider | 52.2Fair value (52.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 113.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mixtral 8x22B Instruct v0.1 π«π·Maker headquartered in FR, 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. | 96.8From 154 benchmarks. Plenty of data behind it. | β 76Β Β±12Coding IQ 75.7, 95% interval 64β88. 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. | $2.00cache read $0.20 | $6.00 | 66K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured |
Llama 3 70b Instruct Abliterated v3.5 Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 95.8From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.70cache read $0.35 | $0.70 | 8K | βNot enough data yet | βNot measured |
Llama 3.1 8B 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. Newer version | 95.6From 343 benchmarks. Plenty of data behind it. | 70Β Β±9Coding IQ 69.9, 95% interval 61β79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.02cache read $0.01 | $0.04 | 131K | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured |
Llama 3.1 8B 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. Newer version | 95.6From 343 benchmarks. Plenty of data behind it. | 70Β Β±9Coding IQ 69.9, 95% interval 61β79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.02cache read $0.01 | $0.03 | 128K | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured |
Llama 3.1 8B Instruct Inference by AwsbedrockπΊπΈMaker 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. Newer version | 95.6From 343 benchmarks. Plenty of data behind it. | 70Β Β±9Coding IQ 69.9, 95% interval 61β79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.231 | $0.231 | βNot published by the provider | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured |
Llama 3.1 8B Instruct Inference by CoreweaveπΊπΈMaker 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. Newer version | 95.6From 343 benchmarks. Plenty of data behind it. | 70Β Β±9Coding IQ 69.9, 95% interval 61β79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.231 | $0.231 | βNot published by the provider | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured |
Llama 3.1 8B Instruct Inference by DeepInfraπΊπΈMaker 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. Newer version | 95.6From 343 benchmarks. Plenty of data behind it. | 70Β Β±9Coding IQ 69.9, 95% interval 61β79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.021 | $0.042 | βNot published by the provider | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured |
Llama 3.1 8B Instruct Inference by GroqπΊπΈMaker 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. Newer version | 95.6From 343 benchmarks. Plenty of data behind it. | 70Β Β±9Coding IQ 69.9, 95% interval 61β79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.0525cache read $0.0263 | $0.084 | βNot published by the provider | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured |
Llama 3.1 8B Instruct Inference by KitaniπΊπΈMaker 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. Newer version | 95.6From 343 benchmarks. Plenty of data behind it. | 70Β Β±9Coding IQ 69.9, 95% interval 61β79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.0514cache read $0.0257 | $0.0803 | βNot published by the provider | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured |
Phi 4 Mini 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. | 95.6From 41 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.17cache read $0.085 | $0.68 | 8K | 40.9Poor value (40.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured |
Phi 4 Mini Inference by KitaniπΊπΈMaker 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. | 95.6From 41 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.1607cache read $0.0803 | $0.693 | βNot published by the provider | 40.9Poor value (40.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured |
MN 12b Mag Mell R1 Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 95.2From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.493cache read $0.2465 | $0.493 | 16K | βNot enough data yet | βNot measured |
Neural Daredevil 8B abliterated Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 95.0From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.44cache read $0.22 | $0.44 | 8K | βNot enough data yet | βNot measured |
Neural Daredevil 8B abliterated Inference by KitaniOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 95.0From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.441cache read $0.2205 | $0.441 | βNot published by the provider | βNot enough data yet | βNot measured |
Doubao Seedream 4-0 Newer version | 93.4From 182 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
FLUX.2 [dev] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 92.4From 183 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
FLUX.2 [dev] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 92.4From 183 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
FLUX.2 [dev] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 92.4From 183 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
FLUX.2 [dev] π©πͺMaker headquartered in DE, according to the company's own website. The citation is on the model page. | 92.4From 183 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
β 92From 13 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet | βNot measured |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)