Listings
All listings: OpenRouter
Every listing for the models on page 13 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter
Sold by OpenRouter
83 listings on this page sold by OpenRouter.
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
- Yap
- Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Yap | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|---|
GPT-4o mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 108.6From 478 benchmarks. Plenty of data behind it. | 72Β Β±18Coding IQ 71.8, 95% interval 54β90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.075 | $0.60 | 128K | 22.1Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 123.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4o mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 108.6From 478 benchmarks. Plenty of data behind it. | 72Β Β±18Coding IQ 71.8, 95% interval 54β90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.075 | $0.60 | 128K | 22.1Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 123.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4o mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 108.6From 478 benchmarks. Plenty of data behind it. | 72Β Β±18Coding IQ 71.8, 95% interval 54β90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.075cache read $0.0375 | $0.30 | 128K | 22.1Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 123.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4o mini Inference by Microsoft AzureπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 108.6From 478 benchmarks. Plenty of data behind it. | 72Β Β±18Coding IQ 71.8, 95% interval 54β90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.075 | $0.60 | 128K | 22.1Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 123.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4o mini Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 108.6From 478 benchmarks. Plenty of data behind it. | 72Β Β±18Coding IQ 71.8, 95% interval 54β90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.075 | $0.60 | 128K | 22.1Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 123.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4o mini Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 108.6From 478 benchmarks. Plenty of data behind it. | 72Β Β±18Coding IQ 71.8, 95% interval 54β90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.075 | $0.60 | 128K | 22.1Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 123.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 27B IT 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. | 108.5From 365 benchmarks. Plenty of data behind it. | 73Β Β±8Coding IQ 72.7, 95% interval 65β81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | βNot published by the provider | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 127.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 27B IT 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. | 108.5From 365 benchmarks. Plenty of data behind it. | 73Β Β±8Coding IQ 72.7, 95% interval 65β81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.08cache read $0.04 | $0.45 | 131K | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 127.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 27B IT 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. | 108.5From 365 benchmarks. Plenty of data behind it. | 73Β Β±8Coding IQ 72.7, 95% interval 65β81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.08 | $0.16 | 131K | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 127.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 27B IT 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. | 108.5From 365 benchmarks. Plenty of data behind it. | 73Β Β±8Coding IQ 72.7, 95% interval 65β81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.064 | $0.128 | 131K | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 127.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 27B IT 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. | 108.5From 365 benchmarks. Plenty of data behind it. | 73Β Β±8Coding IQ 72.7, 95% interval 65β81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.12 | $0.24 | 131K | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 127.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 27B IT Inference by Nebius AI StudioπΊπΈMaker 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. | 108.5From 365 benchmarks. Plenty of data behind it. | 73Β Β±8Coding IQ 72.7, 95% interval 65β81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.04 | $0.30 | 110K | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 127.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 27B IT Inference by NextbitπΊπΈMaker 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. | 108.5From 365 benchmarks. Plenty of data behind it. | 73Β Β±8Coding IQ 72.7, 95% interval 65β81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.08cache read $0.04 | $0.35 | 131K | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 127.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 27B IT Inference by ParasailπΊπΈMaker 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. | 108.5From 365 benchmarks. Plenty of data behind it. | 73Β Β±8Coding IQ 72.7, 95% interval 65β81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.08cache read $0.04 | $0.45 | 131K | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 127.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3 70B Instruct πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 108.2From 199 benchmarks. Plenty of data behind it. | β 77Β Β±11Coding IQ 76.5, 95% interval 66β87. 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. | $0.30 | $0.40 | βNot published by the provider | 49.9Fair value (49.9). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Llama 3.3 70B 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | βNot published by the provider | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.71 | $0.71 | 128K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B Instruct Inference by AkashπΊπΈMaker 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.20cache read $0.10 | $0.52 | 131K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B Instruct Inference by Amazon Web ServicesπΊπΈMaker 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.72 | $0.72 | 131K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B Instruct Inference by Cloudflare Workers AIπΊπΈMaker 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.293 | $2.253 | 24K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.71 | $0.71 | 128K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10 | $0.32 | 131K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B Instruct Inference by GoogleπΊπΈMaker 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.72 | $0.72 | 128K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B Instruct Inference by GoogleπΊπΈMaker 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.72 | $0.72 | 128K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.59cache read $0.295 | $0.79 | 131K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B Instruct Inference by ParasailπΊπΈMaker 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77Β Β±9Coding IQ 77.1, 95% interval 68β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.22cache read $0.11 | $0.50 | 131K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 108.0From 293 benchmarks. Plenty of data behind it. | 72Β Β±9Coding IQ 72.2, 95% interval 63β81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00 | $6.00 | βNot published by the provider | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 108.0From 293 benchmarks. Plenty of data behind it. | 72Β Β±9Coding IQ 72.2, 95% interval 63β81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $6.00 | 128K | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 108.0From 293 benchmarks. Plenty of data behind it. | 72Β Β±9Coding IQ 72.2, 95% interval 63β81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $6.00 | 131K | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 108.0From 293 benchmarks. Plenty of data behind it. | 72Β Β±9Coding IQ 72.2, 95% interval 63β81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $6.00 | 128K | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 108.0From 293 benchmarks. Plenty of data behind it. | 72Β Β±9Coding IQ 72.2, 95% interval 63β81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $6.00 | 131K | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 108.0From 293 benchmarks. Plenty of data behind it. | 72Β Β±9Coding IQ 72.2, 95% interval 63β81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.20cache read $0.22 | $6.60 | 131K | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 108.0From 293 benchmarks. Plenty of data behind it. | 72Β Β±9Coding IQ 72.2, 95% interval 63β81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $6.00 | 131K | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
WizardLM 2 8x22B 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. | β 108From 9 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.50 | $0.50 | βNot published by the provider | 43.8Poor value (43.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Mistral Small 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. | 107.8From 316 benchmarks. Plenty of data behind it. | 78Β Β±10Coding IQ 78.4, 95% interval 68β89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.20 | $0.60 | βNot published by the provider | 27.4Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 59 Β±9Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | βNot measured |
Mistral Small 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. | 107.8From 316 benchmarks. Plenty of data behind it. | 78Β Β±10Coding IQ 78.4, 95% interval 68β89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.015 | $0.60 | 262K | 27.4Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 59 Β±9Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | βNot measured |
Mistral Small Inference by Mistral AIπ«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. | 107.8From 316 benchmarks. Plenty of data behind it. | 78Β Β±10Coding IQ 78.4, 95% interval 68β89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.165cache read $0.0165 | $0.66 | 262K | 27.4Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 59 Β±9Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | βNot measured |
Mistral Small Inference by Mistral AIπ«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. | 107.8From 316 benchmarks. Plenty of data behind it. | 78Β Β±10Coding IQ 78.4, 95% interval 68β89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.165cache read $0.0165 | $0.66 | 262K | 27.4Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 59 Β±9Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | βNot measured |
Mistral Small Inference by Mistral AIπ«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. | 107.8From 316 benchmarks. Plenty of data behind it. | 78Β Β±10Coding IQ 78.4, 95% interval 68β89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.015 | $0.60 | 262K | 27.4Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 59 Β±9Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | βNot measured |
Gemma 3 12B IT 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 | 107.6From 331 benchmarks. Plenty of data behind it. | 68Β Β±19Coding IQ 68.1, 95% interval 49β87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | βNot published by the provider | 41.7Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Gemma 3 12B IT 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 | 107.6From 331 benchmarks. Plenty of data behind it. | 68Β Β±19Coding IQ 68.1, 95% interval 49β87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05 | $0.15 | 131K | 41.7Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Gemma 3 12B IT 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 | 107.6From 331 benchmarks. Plenty of data behind it. | 68Β Β±19Coding IQ 68.1, 95% interval 49β87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05 | $0.15 | 131K | 41.7Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Gemma 3 12B IT 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 | 107.6From 331 benchmarks. Plenty of data behind it. | 68Β Β±19Coding IQ 68.1, 95% interval 49β87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.04 | $0.12 | 131K | 41.7Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Gemma 3 12B IT 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 | 107.6From 331 benchmarks. Plenty of data behind it. | 68Β Β±19Coding IQ 68.1, 95% interval 49β87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.075 | $0.225 | 131K | 41.7Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Gemma 3 12B IT Inference by NextbitπΊπΈMaker 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 | 107.6From 331 benchmarks. Plenty of data behind it. | 68Β Β±19Coding IQ 68.1, 95% interval 49β87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.35cache read $0.05 | $0.45 | 131K | 41.7Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Ministral 8B 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. | 107.6From 73 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.10 | $0.10 | βNot published by the provider | 54.6Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Ministral 8B 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. | 107.6From 73 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15cache read $0.015 | $0.15 | 262K | 54.6Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Ministral 8B Inference by Mistral AIπ«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. | 107.6From 73 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.165cache read $0.0165 | $0.165 | 262K | 54.6Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Ministral 8B Inference by Mistral AIπ«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. | 107.6From 73 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15cache read $0.015 | $0.15 | 262K | 54.6Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
ERNIE 4.5 21B A3B 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. | β 107From 37 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.07 | $0.28 | βNot published by the provider | 46.6Poor value (46.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
ERNIE 4.5 21B A3B 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. | β 107From 37 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.07 | $0.28 | βNot published by the provider | 46.6Poor value (46.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Mixtral 8x22B Instruct 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. | 107.4From 7 benchmarks. A fair amount of data behind it. | βNot enough data yet | $2.00cache read $0.20 | $6.00 | 66K | βNot enough data yet | βNot measured | βNot measured |
Mixtral 8x22B Instruct Inference by Mistral AIπ«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. | 107.4From 7 benchmarks. A fair amount of data behind it. | βNot enough data yet | $2.20cache read $0.22 | $6.60 | 66K | βNot enough data yet | βNot measured | βNot measured |
Mixtral 8x22B Instruct Inference by Mistral AIπ«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. | 107.4From 7 benchmarks. A fair amount of data behind it. | βNot enough data yet | $2.00cache read $0.20 | $6.00 | 66K | βNot enough data yet | βNot measured | βNot measured |
Qwen2 72B Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 107.3From 265 benchmarks. Plenty of data behind it. | β 76Β Β±11Coding IQ 76.2, 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. | $0.90 | $0.90 | βNot published by the provider | 34.3Poor value (34.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Grok Beta πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 107.2From 11 benchmarks. A fair amount of data behind it. | β 78Β Β±11staleCoding IQ 77.6, 95% interval 66β89. 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. Its newest result is over a year old. | $5.00 | $15.00 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
DeepSeek R1 Distill Qwen 32B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 107.1From 40 benchmarks. Plenty of data behind it. | β 81Β Β±12staleCoding IQ 80.5, 95% interval 68β93. 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. Its newest result is over a year old. | $0.12 | $0.18 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
DeepSeek R1 Distill Qwen 14B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 107.0From 24 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15 | $0.15 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Llama 3.1 70B 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 | 106.8From 168 benchmarks. Plenty of data behind it. | β 80Β Β±11Coding IQ 80.3, 95% interval 69β91. 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. | $0.72 | $0.72 | 131K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Llama 3.1 70B Instruct Inference by Amazon Web ServicesπΊπΈMaker 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 | 106.8From 168 benchmarks. Plenty of data behind it. | β 80Β Β±11Coding IQ 80.3, 95% interval 69β91. 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. | $0.72 | $0.72 | 131K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
GPT 4 1106 Preview πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | β 107From 72 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $10.00 | $30.00 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Nova Pro πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 106.4From 119 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.80 | $3.20 | 300K | 36.8Poor value (36.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Nova Pro Inference by Amazon Web ServicesπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 106.4From 119 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.80 | $3.20 | 300K | 36.8Poor value (36.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Nova Pro Inference by Amazon Web ServicesπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 106.4From 119 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.80 | $3.20 | 300K | 36.8Poor value (36.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Llama 4 Scout 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. | 106.3From 347 benchmarks. Plenty of data behind it. | 69Β Β±8Coding IQ 69.3, 95% interval 61β78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | βNot published by the provider | 30.3Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 127.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 4 Scout 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. | 106.3From 347 benchmarks. Plenty of data behind it. | 69Β Β±8Coding IQ 69.3, 95% interval 61β78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10 | $0.30 | 328K | 30.3Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 127.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 4 Scout 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. | 106.3From 347 benchmarks. Plenty of data behind it. | 69Β Β±8Coding IQ 69.3, 95% interval 61β78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10 | $0.30 | 328K | 30.3Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 127.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 4 Scout 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. | 106.3From 347 benchmarks. Plenty of data behind it. | 69Β Β±8Coding IQ 69.3, 95% interval 61β78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.08 | $0.24 | 328K | 30.3Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 127.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 4 Scout 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. | 106.3From 347 benchmarks. Plenty of data behind it. | 69Β Β±8Coding IQ 69.3, 95% interval 61β78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15 | $0.45 | 328K | 30.3Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 127.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 4 Scout Inference by GoogleπΊπΈMaker 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. | 69Β Β±8Coding IQ 69.3, 95% interval 61β78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.25 | $0.70 | 1.3M | 30.3Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 127.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Small 24B Instruct 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. | 106.3From 74 benchmarks. Plenty of data behind it. | β 78Β Β±11Coding IQ 77.9, 95% interval 67β89. 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. | β | β | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Mistral Small 24B Instruct 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. | 106.3From 74 benchmarks. Plenty of data behind it. | β 78Β Β±11Coding IQ 77.9, 95% interval 67β89. 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. | $0.05 | $0.08 | 33K | βNot enough data yet | βNot measured | βNot measured |
Mistral Small 24B Instruct Inference by DeepInfraπ«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. | 106.3From 74 benchmarks. Plenty of data behind it. | β 78Β Β±11Coding IQ 77.9, 95% interval 67β89. 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 | $0.064 | 33K | βNot enough data yet | βNot measured | βNot measured |
Mistral Small 24B Instruct Inference by DeepInfraπ«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. | 106.3From 74 benchmarks. Plenty of data behind it. | β 78Β Β±11Coding IQ 77.9, 95% interval 67β89. 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. | $0.05 | $0.08 | 33K | βNot enough data yet | βNot measured | βNot measured |
Qwen 2.5 Coder 32B Instruct 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. | 106.3From 104 benchmarks. Plenty of data behind it. | 81Β Β±9Coding IQ 80.7, 95% interval 72β89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | βNot published by the provider | 50.7Fair value (50.7). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen 2.5 Coder 32B Instruct 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. | 106.3From 104 benchmarks. Plenty of data behind it. | 81Β Β±9Coding IQ 80.7, 95% interval 72β89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.66 | $1.00 | 33K | 50.7Fair value (50.7). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen 2.5 Coder 32B Instruct Inference by Cloudflare Workers AIπ¨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. | 106.3From 104 benchmarks. Plenty of data behind it. | 81Β Β±9Coding IQ 80.7, 95% interval 72β89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.66 | $1.00 | 33K | 50.7Fair value (50.7). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Gemini 1.5 Flash-8B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 106.1From 50 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.0375cache read $0.01 | $0.15cache write $0.0583 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Llama 3.2 90B 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. | 106.1From 54 benchmarks. Plenty of data behind it. | βNot enough data yet | $1.20 | $1.20 | βNot published by the provider | 57.0Good value (57.0). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Phi 4 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. | 105.9From 144 benchmarks. Plenty of data behind it. | β 78Β Β±11Coding IQ 77.6, 95% interval 66β89. 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. | βNot measured | 129.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Phi 4 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. | 105.9From 144 benchmarks. Plenty of data behind it. | β 78Β Β±11Coding IQ 77.6, 95% interval 66β89. 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 | 4K | 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. | βNot measured | 129.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Phi 4 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. | 105.9From 144 benchmarks. Plenty of data behind it. | β 78Β Β±11Coding IQ 77.6, 95% interval 66β89. 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. | $0.056 | $0.112 | 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. | βNot measured | 129.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3 4B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 105.8From 116 benchmarks. Plenty of data behind it. | β 78Β Β±9Coding IQ 78.4, 95% interval 69β88. 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. | $0.00 | $0.00 | βNot published by the provider | 32.9Poor value (32.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)