Listings
All listings: 302ai
Every listing for the models on page 10 of 16 of 302ai, including each model's other versions and routes. Back to 302ai
Sold by 302ai
34 listings on this page sold by 302ai.
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 |
|---|---|---|---|---|---|---|---|---|
DeepSeek VL2 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 104.8From 23 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.142 | $0.142 | 4K | βNot enough data yet | βNot measured | βNot measured |
Nova Lite πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 104.8From 107 benchmarks. Plenty of data behind it. | β 82Β Β±10Coding IQ 82.3, 95% interval 72β93. 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. | $0.06 | $0.24 | 300K | 41.5Poor value (41.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 38 Β±9Terse (38 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | βNot measured |
Qwen 2.5 14B Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 104.8From 147 benchmarks. Plenty of data behind it. | 76Β Β±10staleCoding IQ 75.7, 95% interval 65β86. 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. | $0.10 | $0.10 | 32K | βNot enough data yet | βNot measured | βNot measured |
Nova Micro πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 103.3From 102 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.035 | $0.14 | 300K | 47.4Poor value (47.4). 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-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 | $0.59 | $0.59 | 32K | βNot enough data yet | βNot measured | βNot measured |
QwQ 32B Preview π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 102.9From 103 benchmarks. Plenty of data behind it. | β 77Β Β±12Coding IQ 76.8, 95% interval 64β89. 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. | $0.29 | $0.86 | 33K | 33.9Poor value (33.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Claude 3 Haiku πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 102.7From 315 benchmarks. Plenty of data behind it. | 76Β Β±10Coding IQ 75.9, 95% interval 66β86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.25cache read $0.05 | $1.25cache write $0.50 | 200K | 33.4Poor value (33.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | 117.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.1 70B 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. | 102.7From 62 benchmarks. Plenty of data behind it. | βNot enough data yet | $1.50 | $1.50 | 128K | βNot enough data yet | βNot measured | 124.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3 1.7B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 101.1From 95 benchmarks. A fair amount of data behind it. | β 76Β Β±9Coding IQ 75.7, 95% interval 66β85. 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 | $0.50 | 29K | βNot enough data yet | βNot measured | βNot measured |
Qwen2.5-VL 7B Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 100.7From 78 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.05 | $0.05 | 32K | 39.1Poor value (39.1). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Ministral 3B π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 100.6From 24 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.33 | $0.33 | 256K | 38.6Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen2.5 Math 7B Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 99.7From 21 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.143 | $0.286 | 4K | βNot enough data yet | βNot measured | βNot measured |
GPT-3.5 Turbo πΊπΈMaker 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. | β 76Β Β±11Coding IQ 75.7, 95% interval 65β87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50 | $1.50 | 16K | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 112.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen2.5 7B 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. | 98.8From 248 benchmarks. Plenty of data behind it. | 73Β Β±9staleCoding IQ 73.2, 95% interval 64β82. 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. | $0.05 | $0.05 | 32K | 54.3Good value (54.3). Cheaper 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-3b-instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 98.6From 46 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.20 | $0.60 | 128K | βNot enough data yet | βNot measured | βNot measured |
Qwen2 57B A14B Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 98.5From 10 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.50 | $1.00 | 64K | βNot enough data yet | βNot measured | βNot measured |
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 | $0.29 | $0.71 | 32K | βNot enough data yet | βNot measured | βNot measured |
Qwen2.5 Coder 7B Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 98.0From 59 benchmarks. Plenty of data behind it. | 77Β Β±11staleCoding IQ 76.6, 95% interval 66β87. 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. | $0.05 | $0.05 | 32K | 54.5Good value (54.5). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
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 | $0.80 | $0.80 | 32K | βNot enough data yet | βNot measured | βNot measured |
Command R+ πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 97.3From 220 benchmarks. Plenty of data behind it. | β 76Β Β±11Coding IQ 75.7, 95% interval 65β87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00 | $3.00 | 4K | βNot enough data yet | βNot measured | βNot measured |
Command R Plus πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 96.9From 196 benchmarks. Plenty of data behind it. | βNot enough data yet | $3.00 | $15.00 | 128K | 21.9Poor value (21.9). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Qwen-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.23 | $0.58 | 32K | 49.8Fair value (49.8). 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-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $2.86 | $2.86 | 32K | 49.8Fair value (49.8). 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-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $2.86 | $2.86 | 32K | 49.8Fair value (49.8). 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-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.43 | $1.29 | 32K | 49.8Fair value (49.8). 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-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.43 | $1.29 | 32K | 49.8Fair value (49.8). 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-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.43 | $1.29 | 128K | 49.8Fair value (49.8). 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-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.43 | $1.29 | 128K | 49.8Fair value (49.8). 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-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.43 | $1.29 | 128K | 49.8Fair value (49.8). 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-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.23 | $0.58 | 128K | 49.8Fair value (49.8). 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-VL Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 96.9From 56 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.23 | $0.572 | 128K | 49.8Fair value (49.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Grok 2 Vision 1212 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 96.5From 34 benchmarks. Plenty of data behind it. | βNot enough data yet | $2.00 | $10.00 | 8K | 31.4Poor value (31.4). 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 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. | $0.06 | $0.06 | 32K | 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 |
Qwen2.5 Coder 1.5b Instruct π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 95.6From 33 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | 32K | βNot enough data yet | βNot measured | βNot measured |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)