Listings
All listings: OpenRouter
Every listing for the models on page 10 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter
Sold by OpenRouter
70 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 |
|---|---|---|---|---|---|---|---|---|
Codestral 25.01 π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 116.6From 10 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.30 | $0.90 | βNot published by the provider | 37.8Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 40 Β±9Terse (40 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 |
Codestral 25.01 π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 116.6From 10 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.30cache read $0.03 | $0.90 | 256K | 37.8Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 40 Β±9Terse (40 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 |
Codestral 25.01 Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 116.6From 10 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.30cache read $0.03 | $0.90 | 256K | 37.8Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 40 Β±9Terse (40 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 |
116.5From 53 benchmarks. Plenty of data behind it. | 93Β Β±13Coding IQ 93.2, 95% interval 80β106. 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 $0.025 | $0.75 | βNot published by the provider | 56.7Good value (56.7). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 43 Β±9Terse (43 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 | |
Mistral Medium 3 π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. Newer version | 116.4From 50 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.44cache read $0.044 | $2.20 | 131K | 51.0Fair value (51.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | 132.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Medium 3 Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. Newer version | 116.4From 50 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.44cache read $0.044 | $2.20 | 131K | 51.0Fair value (51.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | 132.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen Plus π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 116.4From 42 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.26 | $0.78 | βNot published by the provider | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen Plus π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 116.4From 42 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.26 | $0.78cache write $0.325 | βNot published by the provider | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen Plus π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 116.4From 42 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.26cache read $0.052 | $0.78cache write $0.325 | 1M | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen Plus Inference by Alibaba Cloudπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 116.4From 42 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.26cache read $0.052 | $0.78cache write $0.325 | 996K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
DeepSeek V3 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. Newer version | 116.3From 9 benchmarks. A fair amount of data behind it. | βNot enough data yet | β | β | βNot published by the provider | 46.7Poor value (46.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
DeepSeek V3 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. Newer version | 116.3From 9 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.25 | $1.00 | 164K | 46.7Poor value (46.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
DeepSeek V3 Inference by SiliconFlowπ¨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. Newer version | 116.3From 9 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.25 | $1.00 | 164K | 46.7Poor value (46.7). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
GPT-4 Turbo πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 116.2From 380 benchmarks. Plenty of data behind it. | 83Β Β±10Coding IQ 83.0, 95% interval 73β93. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $10.00 | $30.00 | βNot published by the provider | 34.4Poor value (34.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | 125.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4 Turbo πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 116.2From 380 benchmarks. Plenty of data behind it. | 83Β Β±10Coding IQ 83.0, 95% interval 73β93. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $5.00 | $15.00 | 128K | 34.4Poor value (34.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | 125.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3.5 Lightning 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. | 116.2From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.07cache read $0.04 | $0.20 | 262K | 49.3Fair value (49.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Nemotron 3.5 Lightning 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. | 116.2From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.00 | $0.00 | 1M | 49.3Fair value (49.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Nemotron 3.5 Lightning 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. | 116.2From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.07cache read $0.04 | $0.20 | 262K | 49.3Fair value (49.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Nemotron 3.5 Lightning Inference by DarkbloomπΊπΈMaker 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. | 116.2From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.02cache read $0.01 | $0.096 | 262K | 49.3Fair value (49.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Nemotron 3.5 Lightning 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. | 116.2From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.06cache read $0.03 | $0.16 | 262K | 49.3Fair value (49.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Nemotron 3.5 Lightning Inference by Fireworks 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. | 116.2From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.05cache read $0.01 | $0.20 | 262K | 49.3Fair value (49.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Nemotron 3.5 Lightning Inference by ModelrunπΊπΈMaker 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. | 116.2From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.07cache read $0.04 | $0.20 | 1M | 49.3Fair value (49.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Nemotron 3.5 Lightning Inference by NVIDIA NIMπΊπΈMaker 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. | 116.2From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.00 | $0.00 | 1M | 49.3Fair value (49.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen3 Coder 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. | 116.2From 18 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.07 | $0.28 | 262K | 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 |
Qwen3 Coder 30B A3B Instruct Inference by Amazon Web Servicesπ¨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. | 116.2From 18 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.15 | $0.60 | 262K | 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 |
Qwen3 Coder 30B A3B Instruct Inference by SiliconFlowπ¨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. | 116.2From 18 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.07 | $0.28 | 262K | 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 |
Gemini 2.0 Flash πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 116.1From 211 benchmarks. Plenty of data behind it. | β 85Β Β±14staleCoding IQ 84.6, 95% interval 71β98. 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. | $0.10cache read $0.025 | $0.40cache write $0.1833 | βNot published by the provider | 52.1Fair value (52.1). Costs per task about what its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured |
GLM 4.7 Flash 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. Newer version | 116.1From 186 benchmarks. Plenty of data behind it. | 83Β Β±10Coding IQ 82.8, 95% interval 73β93. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.0605cache read $0.01 | $0.40 | 131K | 44.1Poor value (44.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
GLM 4.7 Flash 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. Newer version | 116.1From 186 benchmarks. Plenty of data behind it. | 83Β Β±10Coding IQ 82.8, 95% interval 73β93. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.0605 | $0.40 | 131K | 44.1Poor value (44.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
GLM 4.5V 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. | 115.8From 62 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.60cache read $0.11 | $1.80 | 66K | 36.7Poor value (36.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured |
GLM 4.5V Inference by Novita 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. | 115.8From 62 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.60cache read $0.11 | $1.80 | 66K | 36.7Poor value (36.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured |
GLM 4.5V Inference by Z.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. | 115.8From 62 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.60cache read $0.11 | $1.80 | 66K | 36.7Poor value (36.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured |
QwQ 32B 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. | 115.8From 144 benchmarks. Plenty of data behind it. | 86Β Β±11Coding IQ 86.2, 95% interval 76β97. 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 | $0.20 | βNot published by the provider | 44.6Poor value (44.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 136.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Image πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 115.7From 40 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.50 | $3.00 | 131K | βNot enough data yet | βNot measured | βNot measured |
Gemini 3.1 Flash Image Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 115.7From 40 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.50 | $3.00 | 66K | βNot enough data yet | βNot measured | βNot measured |
Gemini 3.1 Flash Image Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 115.7From 40 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.50 | $3.00 | 131K | βNot enough data yet | βNot measured | βNot measured |
Ministral 14B 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. | 115.6From 33 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.20cache read $0.02 | $0.20 | 262K | βNot enough data yet | βNot measured | βNot measured |
Ministral 14B 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. | 115.6From 33 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.22cache read $0.022 | $0.22 | 262K | βNot enough data yet | βNot measured | βNot measured |
Ministral 14B 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. | 115.6From 33 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.20cache read $0.02 | $0.20 | 262K | βNot enough data yet | βNot measured | βNot measured |
Qwen3 32B 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. | 115.6From 234 benchmarks. Plenty of data behind it. | 85Β Β±9Coding IQ 84.8, 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. | $0.08 | $0.28 | 41K | 35.8Poor value (35.8). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 136.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3 32B Inference by DeepInfraπ¨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. | 115.6From 234 benchmarks. Plenty of data behind it. | 85Β Β±9Coding IQ 84.8, 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. | $0.08 | $0.28 | 41K | 35.8Poor value (35.8). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 136.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3 32B Inference by DeepInfraπ¨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. | 115.6From 234 benchmarks. Plenty of data behind it. | 85Β Β±9Coding IQ 84.8, 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. | $0.064 | $0.224 | 41K | 35.8Poor value (35.8). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 136.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3 32B Inference by DeepInfraπ¨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. | 115.6From 234 benchmarks. Plenty of data behind it. | 85Β Β±9Coding IQ 84.8, 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. | $0.12 | $0.42 | 41K | 35.8Poor value (35.8). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 136.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3 32B Inference by SiliconFlowπ¨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. | 115.6From 234 benchmarks. Plenty of data behind it. | 85Β Β±9Coding IQ 84.8, 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. | $0.14 | $0.57 | 131K | 35.8Poor value (35.8). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 136.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3 32B Inference by Tenstorrentπ¨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. | 115.6From 234 benchmarks. Plenty of data behind it. | 85Β Β±9Coding IQ 84.8, 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. | $0.14cache read $0.09 | $0.40 | 20K | 35.8Poor value (35.8). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 136.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.4From 375 benchmarks. Plenty of data behind it. | 91Β Β±8Coding IQ 91.3, 95% interval 84β99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.10 | $1.60 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 134.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.4From 375 benchmarks. Plenty of data behind it. | 91Β Β±8Coding IQ 91.3, 95% interval 84β99. 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 $0.05 | $0.80 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 134.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 mini Inference by Microsoft AzureπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.4From 375 benchmarks. Plenty of data behind it. | 91Β Β±8Coding IQ 91.3, 95% interval 84β99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.10 | $1.60 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 134.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 mini Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.4From 375 benchmarks. Plenty of data behind it. | 91Β Β±8Coding IQ 91.3, 95% interval 84β99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.10 | $1.60 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 134.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 nano πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.3From 332 benchmarks. Plenty of data behind it. | 93Β Β±13Coding IQ 92.7, 95% interval 80β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05cache read $0.005 | $0.40 | 400K | 46.3Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 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. | 139.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 nano πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.3From 332 benchmarks. Plenty of data behind it. | 93Β Β±13Coding IQ 92.7, 95% interval 80β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.025cache read $0.0025 | $0.20 | 400K | 46.3Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 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. | 139.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 nano Inference by Microsoft AzureπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.3From 332 benchmarks. Plenty of data behind it. | 93Β Β±13Coding IQ 92.7, 95% interval 80β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05cache read $0.01 | $0.40 | 400K | 46.3Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 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. | 139.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 nano Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.3From 332 benchmarks. Plenty of data behind it. | 93Β Β±13Coding IQ 92.7, 95% interval 80β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05cache read $0.005 | $0.40 | 272K | 46.3Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 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. | 139.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 nano Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.3From 332 benchmarks. Plenty of data behind it. | 93Β Β±13Coding IQ 92.7, 95% interval 80β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.025cache read $0.0025 | $0.20 | 400K | 46.3Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 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. | 139.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 nano Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 115.3From 332 benchmarks. Plenty of data behind it. | 93Β Β±13Coding IQ 92.7, 95% interval 80β106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.025cache read $0.0025 | $0.20 | 272K | 46.3Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 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. | 139.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Medium 3.5 π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 115.3From 173 benchmarks. Plenty of data behind it. | 99Β Β±15Coding IQ 98.6, 95% interval 84β114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.50 | $7.50 | 262K | 12.0Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Medium 3.5 π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 115.3From 173 benchmarks. Plenty of data behind it. | 99Β Β±15Coding IQ 98.6, 95% interval 84β114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.75 | $3.75 | 262K | 12.0Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Medium 3.5 Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 115.3From 173 benchmarks. Plenty of data behind it. | 99Β Β±15Coding IQ 98.6, 95% interval 84β114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.75 | $3.75 | 262K | 12.0Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Medium 3.5 Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 115.3From 173 benchmarks. Plenty of data behind it. | 99Β Β±15Coding IQ 98.6, 95% interval 84β114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.65 | $8.25 | 262K | 12.0Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Medium 3.5 Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 115.3From 173 benchmarks. Plenty of data behind it. | 99Β Β±15Coding IQ 98.6, 95% interval 84β114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.50 | $7.50 | 262K | 12.0Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
115.3From 187 benchmarks. Plenty of data behind it. | 83Β Β±14Coding IQ 82.8, 95% interval 69β97. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.10cache read $0.55 | $4.40 | βNot published by the provider | 32.5Poor value (32.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 135.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
115.3From 187 benchmarks. Plenty of data behind it. | 83Β Β±14Coding IQ 82.8, 95% interval 69β97. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.10 | $4.40 | βNot published by the provider | 32.5Poor value (32.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 135.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Gemini 2.0 Flash Lite πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 115.2From 45 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.075 | $0.30 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Nova Premier 1.0 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | β 115From 13 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $2.50cache read $0.625 | $12.50 | 1M | 43.5Poor value (43.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Command A 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. | 115.1From 61 benchmarks. A fair amount of data behind it. | βNot enough data yet | $2.50 | $10.00 | 256K | 31.8Poor value (31.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Command A Inference by CohereπΊπΈMaker 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. | 115.1From 61 benchmarks. A fair amount of data behind it. | βNot enough data yet | $2.50 | $10.00 | 256K | 31.8Poor value (31.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen3 VL 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. | 115.1From 73 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.104 | $0.416 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Reka Flash 3 Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 115.0From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.10 | $0.20 | 66K | 38.8Poor value (38.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Reka Flash 3 Inference by Reka AIOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 115.0From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.10 | $0.20 | 66K | 38.8Poor value (38.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
ERNIE 4.5 300B A47B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 114.9From 12 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.28 | $1.10 | βNot published by the provider | 51.4Fair value (51.4). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)