Listings
All listings: Aihubmix
Every listing for the models on page 11 of 20 of Aihubmix, including each model's other versions and routes. Back to Aihubmix
Sold by Aihubmix
29 listings on this page sold by Aihubmix.
Select a score for details.
About these columns
- llminfo IQ
- llminfo IQ (capability index). How llminfo IQ is computed
- Coding IQ
- llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
- Value
- Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|
GPT-4o mini ๐บ๐ธMaker 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. | 72ย ยฑ18Coding IQ 71.8, 95% interval 54โ90. 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. | 123.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4o mini ๐บ๐ธMaker 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. | 72ย ยฑ18Coding IQ 71.8, 95% interval 54โ90. 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 | โNot published by the provider | 22.1Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | 123.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 27B IT ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 108.5From 365 benchmarks. Plenty of data behind it. | 73ย ยฑ8Coding IQ 72.7, 95% interval 65โ81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.20 | $0.20 | โNot 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. | 127.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3 70B Instruct ๐บ๐ธMaker 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. | โ 77ย ยฑ11Coding IQ 76.5, 95% interval 66โ87. 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. | $0.70 | $0.70 | โNot 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. | โNot measured |
DeepSeek V2 Chat ๐จ๐ณMaker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 108.1From 48 benchmarks. A fair amount of data behind it. | โNot enough data yet | $0.16 | $0.32 | โNot published by the provider | โNot enough data yet | โNot measured |
Llama 3.3 70B Instruct ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 108.1From 278 benchmarks. Plenty of data behind it. | 77ย ยฑ9Coding IQ 77.1, 95% interval 68โ86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60 | $1.20 | 131K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large ๐ซ๐ทMaker 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. | 72ย ยฑ9Coding IQ 72.2, 95% interval 63โ81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $4.00 | $12.00 | โNot published by the provider | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large ๐ซ๐ทMaker 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. | 72ย ยฑ9Coding IQ 72.2, 95% interval 63โ81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00 | $9.00 | โNot published by the provider | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large ๐ซ๐ทMaker 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. | 72ย ยฑ9Coding IQ 72.2, 95% interval 63โ81. 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 | โNot published by the provider | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 3 12B IT ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 107.6From 331 benchmarks. Plenty of data behind it. | 68ย ยฑ19Coding IQ 68.1, 95% interval 49โ87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.20 | $0.20 | โNot 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. | โNot measured |
Qwen2 72B Instruct ๐จ๐ณMaker 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. | โ 76ย ยฑ11Coding IQ 76.2, 95% interval 65โ87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.80 | $0.80 | โNot 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. | โNot measured |
DeepSeek R1 Distill Qwen 32B ๐จ๐ณMaker 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. | โ 81ย ยฑ12staleCoding IQ 80.5, 95% interval 68โ93. 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. | $0.20 | $0.20 | โNot published by the provider | โNot enough data yet | โNot measured |
DeepSeek R1 Distill Qwen 14B ๐จ๐ณMaker 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. | โNot enough data yet | $0.10 | $0.10 | โNot published by the provider | โNot enough data yet | โNot measured |
Llama 3.1 70B Instruct ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 106.8From 168 benchmarks. Plenty of data behind it. | โ 80ย ยฑ11Coding IQ 80.3, 95% interval 69โ91. 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. | $0.60 | $0.78 | โNot published by the provider | 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. | โNot measured |
Llama 3.1 70B Instruct ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 106.8From 168 benchmarks. Plenty of data behind it. | โ 80ย ยฑ11Coding IQ 80.3, 95% interval 69โ91. 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. | $0.02 | $0.02 | โNot published by the provider | 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. | โNot measured |
QVQ 72B Preview ๐จ๐ณMaker headquartered in CN, according to the company's own website. The citation is on the model page. | 106.7From 14 benchmarks. A fair amount of data behind it. | โNot enough data yet | $1.20 | $1.20 | โNot published by the provider | โNot enough data yet | โNot measured |
GPT 4 1106 Preview ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | โ 107From 72 benchmarks. Little data behind it, so treat it as a rough estimate. | โNot enough data yet | $10.00 | $30.00 | โNot published by the provider | โNot enough data yet | โNot measured |
Llama 4 Scout ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 106.3From 347 benchmarks. Plenty of data behind it. | 69ย ยฑ8Coding IQ 69.3, 95% interval 61โ78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.20 | $0.20 | 131K | 30.3Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 127.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen 2.5 Coder 32B Instruct ๐จ๐ณMaker 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. | 81ย ยฑ9Coding IQ 80.7, 95% interval 72โ89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.16 | $0.16 | โNot 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. | โNot measured |
Llama 3.2 90B Vision Instruct ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 106.1From 54 benchmarks. Plenty of data behind it. | โNot enough data yet | $0.50 | $0.50 | โNot 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. | โNot measured |
Meta Llama 3 70b ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 106.1From 92 benchmarks. Plenty of data behind it. | โNot enough data yet | $4.795 | $4.795 | โNot published by the provider | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 121.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Phi 4 ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 105.9From 144 benchmarks. Plenty of data behind it. | โ 78ย ยฑ11Coding IQ 77.6, 95% interval 66โ89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.12 | $0.48 | 16K | 51.2Fair value (51.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 129.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3 4B ๐จ๐ณMaker 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. | โ 78ย ยฑ9Coding IQ 78.4, 95% interval 69โ88. 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. | $0.046 | $0.46 | โNot published by the provider | 32.9Poor value (32.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | โNot measured |
Jamba 1.5 Large ๐ฎ๐ฑMaker headquartered in IL, according to the company's own website. The citation is on the model page. | 105.4From 113 benchmarks. Plenty of data behind it. | โNot enough data yet | $2.20 | $8.80 | โNot published by the provider | 27.7Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | โNot measured |
GPT-4.1 nano ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75ย ยฑ9Coding IQ 74.7, 95% interval 66โ83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025 | $0.40 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 2.5 Flash Image ๐บ๐ธMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | โNot enough data yet | $0.30cache read $0.03 | $2.499 | 66K | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | โNot measured |
GLM 4 Vision ๐จ๐ณMaker headquartered in CN, according to the company's own website. The citation is on the model page. | 104.9From 19 benchmarks. Plenty of data behind it. | โNot enough data yet | $14.20 | $14.20 | โNot published by the provider | โNot enough data yet | โNot measured |
DeepSeek VL2 ๐จ๐ณMaker 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. | โNot enough data yet | $0.16 | $0.16 | โNot published by the provider | โNot enough data yet | โNot measured |
Qwen 2.5 14B Instruct ๐จ๐ณMaker 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. | 76ย ยฑ10staleCoding IQ 75.7, 95% interval 65โ86. 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. | $0.40 | $1.20 | โNot published by the provider | โNot enough data yet | โNot measured |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)