Listings
All listings: Nebius AI Studio
Every listing for the models on page 3 of 4 of Nebius AI Studio, including each model's other versions and routes. Back to Nebius AI Studio
Sold by Nebius AI Studio
24 listings on this page sold by Nebius AI Studio.
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 |
|---|---|---|---|---|---|---|---|---|
Qwen3 30B A3B 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. | 114.9From 100 benchmarks. Plenty of data behind it. | β 86Β Β±20Coding IQ 86.4, 95% interval 67β106. 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. | $0.10 | $0.30 | 262K | 36.5Poor value (36.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 134.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 114.5From 492 benchmarks. Plenty of data behind it. | 85Β Β±7Coding IQ 85.3, 95% interval 79β92. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50 | $1.50 | 128K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 47 Β±9Typical (47 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 135.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 114.5From 492 benchmarks. Plenty of data behind it. | 85Β Β±7Coding IQ 85.3, 95% interval 79β92. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50 | $1.50 | 128K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 47 Β±9Typical (47 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 135.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3 30B 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. | 114.4From 142 benchmarks. Plenty of data behind it. | 90Β Β±10Coding IQ 90.3, 95% interval 80β101. 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 | 33K | 35.8Poor value (35.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 138.3Epoch Capabilities IndexSetting: thinkingSource: Epoch AI Benchmarking Hub API |
Qwen3 14B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 114.1From 210 benchmarks. Plenty of data behind it. | 85Β Β±9Coding IQ 84.9, 95% interval 76β94. 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 | 33K | 33.7Poor value (33.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 136.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.1 405B Instruct πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 111.8From 123 benchmarks. Plenty of data behind it. | 84Β Β±9Coding IQ 84.3, 95% interval 76β93. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00 | $3.00 | 128K | 41.9Poor value (41.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
BGE multilingual gemma2 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. | 111.1From 38 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.01 | β | 8K | βNot enough data yet | βNot measured | βNot measured |
E5 Mistral 7B Instruct Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 110.1From 159 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.01 | β | 33K | βNot enough data yet | βNot measured | βNot measured |
Nemotron 3 Nano 30B A3B 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. | 109.7From 137 benchmarks. Plenty of data behind it. | 91Β Β±14Coding IQ 91.4, 95% interval 77β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.06cache read $0.012 | $0.24 | 262K | 36.7Poor value (36.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen2.5 32B Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 109.0From 108 benchmarks. Plenty of data behind it. | 78Β Β±10staleCoding IQ 77.8, 95% interval 67β88. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old. | $0.06 | $0.20 | 128K | βNot enough data yet | βNot measured | βNot measured |
Qwen2.5 72B Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 108.9From 216 benchmarks. Plenty of data behind it. | 80Β Β±22Coding IQ 79.9, 95% interval 58β102. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.13 | $0.40 | 128K | 35.0Poor value (35.0). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Qwen2.5 VL 72B 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. | 108.8From 97 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.25 | $0.75 | 32K | 41.2Poor value (41.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
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. | $0.10cache 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 |
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. | $0.13 | $0.40 | 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 |
BGE En Icl 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. | 107.4From 13 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.01 | β | 33K | 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. | $0.13 | $0.40 | 128K | 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 |
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. | $0.08 | $0.24 | 33K | 32.9Poor value (32.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured |
Qwen2-VL (72B) Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 103.1From 34 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.13 | $0.40 | 131K | βNot enough data yet | βNot measured | βNot measured |
Qwen2.5-Coder-7B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 99.3From 11 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.01 | $0.03 | 33K | βNot enough data yet | βNot measured | 107.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen2 VL 7b Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 98.3From 30 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.02 | $0.06 | 131K | βNot enough data yet | βNot measured | βNot measured |
Mistral Nemo π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 98.1From 85 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.04 | $0.12 | 128K | 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. | βNot measured | 113.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek R1 Distill Llama 70B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 97.6From 6 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.25 | $0.75 | 128K | βNot enough data yet | βNot measured | βNot measured |
Llama 3.1 8B Instruct πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 95.6From 343 benchmarks. Plenty of data behind it. | 70Β Β±9Coding IQ 69.9, 95% interval 61β79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.02 | $0.06 | 128K | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Llama Guard 3 8B πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.02 | $0.06 | 128K | 49.6Fair value (49.6). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Run by Nebius AI Studio
24 listings on this page where Nebius AI Studio 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
- 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 | Provider | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Yap | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|---|---|
Qwen3 30B A3B 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. | 114.9From 100 benchmarks. Plenty of data behind it. | β 86Β Β±20Coding IQ 86.4, 95% interval 67β106. 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 | 262K | 36.5Poor value (36.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 134.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3 30B A3B 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. | 114.9From 100 benchmarks. Plenty of data behind it. | β 86Β Β±20Coding IQ 86.4, 95% interval 67β106. 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. | $0.10 | $0.30 | 262K | 36.5Poor value (36.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 134.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3 30B A3B 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. | 114.9From 100 benchmarks. Plenty of data behind it. | β 86Β Β±20Coding IQ 86.4, 95% interval 67β106. 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. | $0.10 | $0.30 | 262K | 36.5Poor value (36.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 134.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3 30B A3B 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. | 114.9From 100 benchmarks. Plenty of data behind it. | β 86Β Β±20Coding IQ 86.4, 95% interval 67β106. 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. | $0.10 | $0.30 | 262K | 36.5Poor value (36.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 134.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3 30B A3B 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. | 114.9From 100 benchmarks. Plenty of data behind it. | β 86Β Β±20Coding IQ 86.4, 95% interval 67β106. 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. | $0.10 | $0.30 | 128K | 36.5Poor value (36.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 134.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V3 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 114.5From 492 benchmarks. Plenty of data behind it. | 85Β Β±7Coding IQ 85.3, 95% interval 79β92. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.75 | $2.25 | 33K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 47 Β±9Typical (47 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 135.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3 30B 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. | 114.4From 142 benchmarks. Plenty of data behind it. | 90Β Β±10Coding IQ 90.3, 95% interval 80β101. 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 | 262K | 35.8Poor value (35.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 138.3Epoch Capabilities IndexSetting: thinkingSource: Epoch AI Benchmarking Hub API | |
Qwen3 30B 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. | 114.4From 142 benchmarks. Plenty of data behind it. | 90Β Β±10Coding IQ 90.3, 95% interval 80β101. 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 | βNot published by the provider | 35.8Poor value (35.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 138.3Epoch Capabilities IndexSetting: thinkingSource: Epoch AI Benchmarking Hub API | |
Qwen3 14B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 114.1From 210 benchmarks. Plenty of data behind it. | 85Β Β±9Coding IQ 84.9, 95% interval 76β94. 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 | βNot published by the provider | 33.7Poor value (33.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 136.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Nemotron 3 Nano 30B A3B 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. | 109.7From 137 benchmarks. Plenty of data behind it. | 91Β Β±14Coding IQ 91.4, 95% interval 77β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | β | β | 256K | 36.7Poor value (36.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured | |
Nemotron 3 Nano 30B A3B 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. | 109.7From 137 benchmarks. Plenty of data behind it. | 91Β Β±14Coding IQ 91.4, 95% interval 77β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.06 | $0.24 | 262K | 36.7Poor value (36.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured | |
Nemotron 3 Nano 30B A3B 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. | 109.7From 137 benchmarks. Plenty of data behind it. | 91Β Β±14Coding IQ 91.4, 95% interval 77β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.06cache read $0.012 | $0.24 | 262K | 36.7Poor value (36.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured | |
Qwen2.5 VL 72B 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. | 108.8From 97 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.25 | $0.75 | 32K | 41.2Poor value (41.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured | |
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. | β | β | 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 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. | $0.10 | $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 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. | $0.10 | $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 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. | $0.10cache 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 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. | $0.10 | $0.30 | 128K | 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 3.3 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. | $0.25 | $0.75 | 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 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. | $0.13 | $0.40 | 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 | |
Gemma 2 9B IT πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 102.3From 133 benchmarks. Plenty of data behind it. | β 76Β Β±10Coding IQ 75.7, 95% interval 65β86. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.03 | $0.09 | 8K | βNot enough data yet | βNot measured | βNot measured | |
Qwen2.5-Coder-7B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 99.3From 11 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.03 | $0.09 | 33K | βNot enough data yet | βNot measured | 107.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Llama 3.1 8B Instruct πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 95.6From 343 benchmarks. Plenty of data behind it. | 70Β Β±9Coding IQ 69.9, 95% interval 61β79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.03 | $0.09 | 131K | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured | |
Gemma 2 2B IT πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 94.5From 80 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.02 | $0.06 | 8K | βNot enough data yet | βNot measured | βNot measured |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)