Listings
All listings: Microsoft Azure
Every listing for the models on page 6 of 13 of Microsoft Azure, including each model's other versions and routes. Back to Microsoft Azure
Sold by Microsoft Azure
69 listings on this page sold by Microsoft Azure.
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 |
|---|---|---|---|---|---|---|---|
GPT 4 1106 Preview ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | โ 107From 72 benchmarks. Little data behind it, so treat it as a rough estimate. | โNot enough data yet | $10.00 | $30.00 | 128K | โNot enough data yet | โNot measured |
GPT 4 1106 Preview ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | โ 107From 72 benchmarks. Little data behind it, so treat it as a rough estimate. | โNot enough data yet | $5.00 | $15.00 | โNot published by the provider | โNot enough data yet | โNot measured |
โ 106From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | โNot enough data yet | $1.50 | $2.00 | โNot published by the provider | โNot enough data yet | โNot measured | |
Llama 4 Scout ๐บ๐ธMaker 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. | 106.3From 347 benchmarks. Plenty of data behind it. | 69ย ยฑ8Coding IQ 69.3, 95% interval 61โ78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.20 | $0.78 | 10M | 30.3Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 127.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Phi-4-reasoning ๐บ๐ธMaker 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. | 106.2From 13 benchmarks. A fair amount of data behind it. | โNot enough data yet | $0.125 | $0.50 | 33K | โNot enough data yet | โNot measured |
Phi 4 ๐บ๐ธMaker 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. | 105.9From 144 benchmarks. Plenty of data behind it. | โ 78ย ยฑ11Coding IQ 77.6, 95% interval 66โ89. 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. | $0.07 | $0.14 | 16K | 51.2Fair value (51.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 129.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4-0125-preview ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.5From 42 benchmarks. A fair amount of data behind it. | โNot enough data yet | $10.00 | $30.00 | 128K | โNot enough data yet | โNot measured |
GPT-4-0125-preview ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.5From 42 benchmarks. A fair amount of data behind it. | โNot enough data yet | $5.00 | $15.00 | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025batch $0.05 | $0.40batch $0.20 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer versiongpt-4.1-nano-2025-04-14 ยท 2025-04-14 ยท ๐ฆ๐บ๐ง๐ท+18 australia-east, brazil-south +26gpt-4.1-nano-2025-04-14 ยท 2025-04-14 ยท ๐ฆ๐บ๐ง๐ท+18 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, italy-north, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, asia-pacific-southeast, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-2, us-west-3 | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025batch $0.05 | $0.40batch $0.20 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.11cache read $0.028 | $0.44 | โNot published by the provider | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.11cache read $0.028 | $0.44 | โNot published by the provider | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05 | $0.20 | โNot published by the provider | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05 | $0.20 | โNot published by the provider | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Phi 4 Multimodal Instruct ๐บ๐ธMaker 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. | โNot enough data yet | $0.05 | $0.10 | 131K | 59.1Good value (59.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | โNot measured |
Phi-3 Medium 128K Instruct ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 101.7From 29 benchmarks. Plenty of data behind it. | โNot enough data yet | $1.00 | $1.00 | โNot published by the provider | โNot enough data yet | โNot measured |
Sora 2 Pro ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | โ 102From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
Text Davinci 003 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | โ 101From 14 benchmarks. Little data behind it, so treat it as a rough estimate. | โNot enough data yet | $20.00 | $20.00 | โNot published by the provider | โNot enough data yet | โNot measured |
Text Davinci 003 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | โ 101From 14 benchmarks. Little data behind it, so treat it as a rough estimate. | โNot enough data yet | $10.00 | $10.00 | โNot published by the provider | โNot enough data yet | โNot measured |
Text Embedding 3 Small ๐บ๐ธMaker 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. | โNot enough data yet | $0.02 | โ | 8K | โNot enough data yet | โNot measured |
Text Embedding 3 Small ๐บ๐ธMaker 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. | โNot enough data yet | $0.01 | โ | โNot published by the provider | โNot enough data yet | โNot measured |
Text Embedding Ada 002 ๐บ๐ธMaker 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. | โNot enough data yet | $0.10 | โ | 8K | โNot enough data yet | โNot measured |
Text Embedding Ada 002 ๐บ๐ธMaker 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. | โNot enough data yet | $0.05 | โ | โNot published by the provider | โNot enough data yet | โNot measured |
Text Embedding Ada 002 ๐บ๐ธMaker 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. | โNot enough data yet | $0.05 | โ | โNot published by the provider | โNot enough data yet | โNot measured |
Text Embedding Ada 002 ๐บ๐ธMaker 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. | โNot enough data yet | $0.10 | โ | โNot published by the provider | โNot enough data yet | โNot measured |
FLUX.2 [flex] ๐ฉ๐ชMaker 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. | โNot enough data yet | โ | โ | 32K | โNot enough data yet | โNot measured |
Ministral 3B ๐ซ๐ทMaker 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. | โNot enough data yet | $0.04 | $0.04 | 128K | 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. | โNot measured |
GPT Image 1 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. ๐ฆ๐บ๐ง๐ท+17 australia-east, brazil-south +22๐ฆ๐บ๐ง๐ท+17 australia-east, brazil-south, canada-east, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3 | 100.1From 45 benchmarks. A fair amount of data behind it. | โNot enough data yet | $5.00cache read $1.25 | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. data-zone ยท ๐บ๐ธ๐ซ๐ท+6 us-east, us-east-2 +11data-zone ยท ๐บ๐ธ๐ซ๐ท+6 us-east, us-east-2, france-central, germany-west-central, us-north-central, europe-north, poland-central, us-south-central, spain-central, sweden-central, europe-west, us-west, us-west-3 | 100.1From 45 benchmarks. A fair amount of data behind it. | โNot enough data yet | $5.50 | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. regional ยท ๐บ๐ธ๐ฎ๐ช+17 us-east, us-east-2 +22regional ยท ๐บ๐ธ๐ฎ๐ช+17 us-east, us-east-2, us-north-central, europe-north, us-south-central, sweden-central, us-west, us-west-3, australia-east, brazil-south, canada-east, france-central, germany-west-central, japan-east, korea-central, norway-east, poland-central, south-africa-north, south-india, spain-central, switzerland-north, uae-north, united-kingdom-south, europe-west | 100.1From 45 benchmarks. A fair amount of data behind it. | โNot enough data yet | $5.50cache read $1.25 | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker 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. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker 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. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker 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. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker 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. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker 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. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker 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. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker 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. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker 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. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT Image 1 ๐บ๐ธMaker 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. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. ๐ฆ๐บ๐ง๐ท+17 australia-east, brazil-south +22๐ฆ๐บ๐ง๐ท+17 australia-east, brazil-south, canada-east, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3 | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | $2.00cache read $0.20 | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
GPT-Image-1 mini ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 23 benchmarks. A fair amount of data behind it. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
Text Davinci 002 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 17 benchmarks. A fair amount of data behind it. | โNot enough data yet | $20.00 | $20.00 | โNot published by the provider | โNot enough data yet | โNot measured |
Text Davinci 002 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 100.1From 17 benchmarks. A fair amount of data behind it. | โNot enough data yet | $10.00 | $10.00 | โNot published by the provider | โNot enough data yet | โNot measured |
FLUX.2 [pro] ๐ฉ๐ชMaker 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. | โNot enough data yet | โ | โ | 32K | โNot enough data yet | โNot measured |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer versiongpt-3.5-turbo-0125 ยท 0125 ยท ๐ฆ๐บ๐จ๐ฆ+8 australia-east, canada-east +15gpt-3.5-turbo-0125 ยท 0125 ยท ๐ฆ๐บ๐จ๐ฆ+8 australia-east, canada-east, us-east, us-east-2, france-central, japan-east, us-north-central, us-south-central, south-india, sweden-central, switzerland-north, united-kingdom-south, usgov-arizona, usgov-virginia, europe-west, us-west, us-west-3 | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $0.55 | $1.65 | 16K | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer versiongpt-3.5-turbo-0301 ยท 0301 ยท ๐ฆ๐บ๐จ๐ฆ+6 australia-east, canada-east +8gpt-3.5-turbo-0301 ยท 0301 ยท ๐ฆ๐บ๐จ๐ฆ+6 australia-east, canada-east, us-east, us-east-2, france-central, japan-east, us-north-central, sweden-central, switzerland-north, united-kingdom-south | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $1.50 | $2.00 | โNot published by the provider | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer versiongpt-3.5-turbo-0613 ยท 0613 ยท ๐ฆ๐บ๐จ๐ฆ+6 australia-east, canada-east +8gpt-3.5-turbo-0613 ยท 0613 ยท ๐ฆ๐บ๐จ๐ฆ+6 australia-east, canada-east, us-east, us-east-2, france-central, japan-east, us-north-central, sweden-central, switzerland-north, united-kingdom-south | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $1.50 | $2.00 | โNot published by the provider | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer versiongpt-3.5-turbo-1106 ยท 1106 ยท ๐ฆ๐บ๐จ๐ฆ+5 australia-east, canada-east +7gpt-3.5-turbo-1106 ยท 1106 ยท ๐ฆ๐บ๐จ๐ฆ+5 australia-east, canada-east, france-central, south-india, sweden-central, united-kingdom-south, usgov-arizona, usgov-virginia, us-west | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $1.10 | $2.20 | 16K | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $1.50 | $2.00 | 4K | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $0.75 | $1.00 | โNot published by the provider | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $0.25 | $0.75 | โNot published by the provider | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $0.75 | $1.00 | โNot published by the provider | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $0.75 | $1.00 | โNot published by the provider | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $0.50 | $1.00 | โNot published by the provider | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Nemo ๐ซ๐ทMaker 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. | โNot enough data yet | $0.15 | $0.15 | 131K | 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 |
Phi-3 Mini 128K Instruct ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 97.6From 41 benchmarks. Plenty of data behind it. | โNot enough data yet | $0.10 | $0.10 | โNot published by the provider | 44.5Poor value (44.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | โNot measured |
Phi 4 Mini ๐บ๐ธMaker 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. | โNot enough data yet | $0.08 | $0.35 | 131K | 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. | โNot measured |
text-davinci-001 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 90.7From 12 benchmarks. Plenty of data behind it. | โNot enough data yet | $20.00 | $20.00 | โNot published by the provider | โNot enough data yet | โNot measured |
text-davinci-001 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | 90.7From 12 benchmarks. Plenty of data behind it. | โNot enough data yet | $10.00 | $10.00 | โNot published by the provider | โNot enough data yet | โNot measured |
davinci ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | โ 89From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | โNot enough data yet | โ | โ | โNot published by the provider | โNot enough data yet | โNot measured |
davinci ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. | โ 89From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | โNot enough data yet | $10.00 | $10.00 | โNot published by the provider | โNot enough data yet | โNot measured |
Run by Microsoft Azure
14 listings on this page where Microsoft Azure 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
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | Provider | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|---|
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | โ | โ | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025 | $0.40 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.11cache read $0.0275 | $0.44 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.11cache read $0.0275 | $0.44 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025 | $0.40 | โNot published by the provider | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.03 | $0.40 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025 | $0.40 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025 | $0.40 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.11cache read $0.0275 | $0.44 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.11cache read $0.0275 | $0.44 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025 | $0.40 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Text Embedding 3 Small ๐บ๐ธMaker 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. | โNot enough data yet | $0.02 | โ | โNot published by the provider | โNot enough data yet | โNot measured | |
Text Embedding Ada 002 ๐บ๐ธMaker 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. | โNot enough data yet | $0.10 | โ | โNot published by the provider | โNot enough data yet | โNot measured | |
GPT-3.5 Turbo ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 99.4From 417 benchmarks. Plenty of data behind it. | โ 76ย ยฑ11Coding IQ 75.7, 95% interval 65โ87. 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. | $1.00 | $2.00 | 4K | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)