Listings
All listings: Llmgateway
Every listing for the models on page 4 of 13 of Llmgateway, including each model's other versions and routes. Back to Llmgateway
Sold by Llmgateway
91 listings on this page sold by Llmgateway.
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 |
|---|---|---|---|---|---|---|---|---|
131.7From 584 benchmarks. Plenty of data behind it. | 111Β Β±5Coding IQ 110.8, 95% interval 106β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.125 | $10.00 | βNot published by the provider | 52.5Fair value (52.5). Costs per task about what its benchmark results predict. Plenty of data behind it. | 65 Β±8Chatty (65 Β±8). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it. | 150Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
131.7From 584 benchmarks. Plenty of data behind it. | 111Β Β±5Coding IQ 110.8, 95% interval 106β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.125 | $10.00 | βNot published by the provider | 52.5Fair value (52.5). Costs per task about what its benchmark results predict. Plenty of data behind it. | 65 Β±8Chatty (65 Β±8). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it. | 150Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Hy4 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 16 Nov 2026 | 131.7From 26 benchmarks. Plenty of data behind it. | β 115Β Β±24Coding IQ 115.3, 95% interval 91β140. 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. | $0.07cache read $0.003 | $0.281 | 1M | 65.5Good value (65.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 Β±9Terse (40 Β±9). Generates fewer tokens than models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | βNot measured |
Qwen3 Embedding 8B 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. | 131.7From 196 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.01 | β | 41K | βNot enough data yet | βNot measured | βNot measured |
Qwen3 Embedding 8B 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. | 131.7From 196 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.01 | β | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Qwen3 Embedding 8B Inference by Nebius AI Studioπ¨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. | 131.7From 196 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.01 | β | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
131.0From 352 benchmarks. Plenty of data behind it. | 107Β Β±8Coding IQ 106.6, 95% interval 99β114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.125 | $10.00 | βNot published by the provider | 49.7Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 50 Β±9Typical (50 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. | 150.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
131.0From 352 benchmarks. Plenty of data behind it. | 107Β Β±8Coding IQ 106.6, 95% interval 99β114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.125 | $10.00 | βNot published by the provider | 49.7Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 50 Β±9Typical (50 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. | 150.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.1 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 | 130.8From 224 benchmarks. Plenty of data behind it. | 110Β Β±6Coding IQ 110.0, 95% interval 104β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.38cache read $0.26 | $4.40 | 205K | 43.2Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±8Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5.1 Inference by Alibaba Cloudπ¨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 | 130.8From 224 benchmarks. Plenty of data behind it. | 110Β Β±6Coding IQ 110.0, 95% interval 104β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.26 | $4.40 | βNot published by the provider | 43.2Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±8Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5.1 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. Newer version | 130.8From 224 benchmarks. Plenty of data behind it. | 110Β Β±6Coding IQ 110.0, 95% interval 104β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.05cache read $0.205 | $3.50 | βNot published by the provider | 43.2Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±8Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5.1 Inference by Nebius AI Studioπ¨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 | 130.8From 224 benchmarks. Plenty of data behind it. | 110Β Β±6Coding IQ 110.0, 95% interval 104β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40 | $4.40 | βNot published by the provider | 43.2Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±8Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5.1 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. Newer version | 130.8From 224 benchmarks. Plenty of data behind it. | 110Β Β±6Coding IQ 110.0, 95% interval 104β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.38cache read $0.26 | $4.40 | βNot published by the provider | 43.2Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±8Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5.1 Inference by Together 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 | 130.8From 224 benchmarks. Plenty of data behind it. | 110Β Β±6Coding IQ 110.0, 95% interval 104β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.26 | $4.40 | βNot published by the provider | 43.2Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±8Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5.1 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. Newer version | 130.8From 224 benchmarks. Plenty of data behind it. | 110Β Β±6Coding IQ 110.0, 95% interval 104β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.26 | $4.40 | βNot published by the provider | 43.2Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 51 Β±8Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Pro 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. | 130.7From 303 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.6, 95% interval 98β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.66cache read $0.022 | $1.98 | 1.1M | 46.9Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 43 Β±10Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Pro Inference by Alibaba Cloudπ¨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. | 130.7From 303 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.6, 95% interval 98β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.32cache read $0.132 | $3.96 | βNot published by the provider | 46.9Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 43 Β±10Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Pro 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. | 130.7From 303 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.6, 95% interval 98β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.32cache read $0.044 | $3.96 | βNot published by the provider | 46.9Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 43 Β±10Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Pro 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. | 130.7From 303 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.6, 95% interval 98β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.30cache read $0.10 | $2.60 | βNot published by the provider | 46.9Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 43 Β±10Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Pro Inference by DeepSeekπ¨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. | 130.7From 303 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.6, 95% interval 98β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.66cache read $0.022 | $1.98 | βNot published by the provider | 46.9Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 43 Β±10Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Pro Inference by Fireworks 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. | 130.7From 303 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.6, 95% interval 98β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.32cache read $0.044 | $3.96 | βNot published by the provider | 46.9Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 43 Β±10Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Pro Inference by Nebius AI Studioπ¨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. | 130.7From 303 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.6, 95% interval 98β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.75 | $3.50 | βNot published by the provider | 46.9Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 43 Β±10Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Pro Inference by Together 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. | 130.7From 303 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.6, 95% interval 98β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.32cache read $0.13 | $3.96 | βNot published by the provider | 46.9Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 43 Β±10Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 150.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.5 397B A17B 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. | 130.6From 367 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.8, 95% interval 98β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60 | $3.60 | 262K | 48.4Fair value (48.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 46 Β±9Typical (46 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. | 148Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.5 397B A17B Inference by Alibaba Cloudπ¨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. | 130.6From 367 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.8, 95% interval 98β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60 | $3.60 | βNot published by the provider | 48.4Fair value (48.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 46 Β±9Typical (46 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. | 148Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.5 397B A17B Inference by Nebius AI Studioπ¨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. | 130.6From 367 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.8, 95% interval 98β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60 | $3.60 | βNot published by the provider | 48.4Fair value (48.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 46 Β±9Typical (46 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. | 148Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.5 397B A17B 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. | 130.6From 367 benchmarks. Plenty of data behind it. | 105Β Β±7Coding IQ 104.8, 95% interval 98β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60 | $3.60 | βNot published by the provider | 48.4Fair value (48.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 46 Β±9Typical (46 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. | 148Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Beam 1.0 501B A23B Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 130.0From 84 benchmarks. Plenty of data behind it. | 109Β Β±6Coding IQ 109.0, 95% interval 103β115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.04 | $1.20 | 1M | βNot enough data yet | βNot measured | βNot measured |
Beam 1.0 501B A23B Inference by Together AIOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 130.0From 84 benchmarks. Plenty of data behind it. | 109Β Β±6Coding IQ 109.0, 95% interval 103β115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.04 | $1.20 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Claude Sonnet 4.5 Inference by Amazon Web ServicesπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 129.7From 442 benchmarks. Plenty of data behind it. | 107Β Β±7Coding IQ 107.2, 95% interval 101β114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00cache read $0.30 | $15.00cache write $3.75 | βNot published by the provider | 40.2Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 Β±8Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Sonnet 4.5 Inference by Amazon Web ServicesπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 129.7From 442 benchmarks. Plenty of data behind it. | 107Β Β±7Coding IQ 107.2, 95% interval 101β114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00cache read $0.30 | $15.00cache write $3.75 | βNot published by the provider | 40.2Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 Β±8Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Sonnet 4.5 Inference by AnthropicπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 129.7From 442 benchmarks. Plenty of data behind it. | 107Β Β±7Coding IQ 107.2, 95% interval 101β114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00cache read $0.30 | $15.00cache write $3.75 | βNot published by the provider | 40.2Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 Β±8Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Sonnet 4.5 Inference by AnthropicπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 129.7From 442 benchmarks. Plenty of data behind it. | 107Β Β±7Coding IQ 107.2, 95% interval 101β114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00cache read $0.30 | $15.00cache write $3.75 | βNot published by the provider | 40.2Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 Β±8Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Sonnet 4.5 Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 129.7From 442 benchmarks. Plenty of data behind it. | 107Β Β±7Coding IQ 107.2, 95% interval 101β114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00cache read $0.30 | $15.00cache write $3.75 | βNot published by the provider | 40.2Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 Β±8Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
129.7From 306 benchmarks. Plenty of data behind it. | 107Β Β±5Coding IQ 106.7, 95% interval 102β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.573 | $2.58 | 203K | 49.7Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 55 Β±9Typical (55 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. | 146.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
129.7From 306 benchmarks. Plenty of data behind it. | 107Β Β±5Coding IQ 106.7, 95% interval 102β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.573 | $2.58 | βNot published by the provider | 49.7Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 55 Β±9Typical (55 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. | 146.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
129.7From 306 benchmarks. Plenty of data behind it. | 107Β Β±5Coding IQ 106.7, 95% interval 102β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00 | $3.20 | βNot published by the provider | 49.7Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 55 Β±9Typical (55 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. | 146.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
129.7From 306 benchmarks. Plenty of data behind it. | 107Β Β±5Coding IQ 106.7, 95% interval 102β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00cache read $0.20 | $3.20 | βNot published by the provider | 49.7Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 55 Β±9Typical (55 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. | 146.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
129.7From 306 benchmarks. Plenty of data behind it. | 107Β Β±5Coding IQ 106.7, 95% interval 102β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00 | $3.20 | βNot published by the provider | 49.7Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 55 Β±9Typical (55 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. | 146.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
129.7From 306 benchmarks. Plenty of data behind it. | 107Β Β±5Coding IQ 106.7, 95% interval 102β112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00cache read $0.20 | $3.20 | βNot published by the provider | 49.7Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it. | 55 Β±9Typical (55 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. | 146.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Mistral Large 4 π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 129.6From 173 benchmarks. Plenty of data behind it. | 115Β Β±7Coding IQ 114.7, 95% interval 108β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.36cache read $0.14 | $4.18 | 1M | 30.8Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 Β±9Chatty (62 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large 4 Inference by Mistral AIπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 129.6From 173 benchmarks. Plenty of data behind it. | 115Β Β±7Coding IQ 114.7, 95% interval 108β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.36cache read $0.14 | $4.18 | βNot published by the provider | 30.8Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 Β±9Chatty (62 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.7 Plus π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 129.5From 260 benchmarks. Plenty of data behind it. | 109Β Β±6Coding IQ 108.7, 95% interval 103β115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.08 | $1.60cache write $0.50 | 984K | 47.1Poor value (47.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | 59 Β±9Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.7 Plus Inference by Alibaba Cloudπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 129.5From 260 benchmarks. Plenty of data behind it. | 109Β Β±6Coding IQ 108.7, 95% interval 103β115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.08 | $1.60cache write $0.50 | βNot published by the provider | 47.1Poor value (47.1). Costs more per task than its benchmark results predict. Plenty of data behind it. | 59 Β±9Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.6 Plus π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 129.4From 256 benchmarks. Plenty of data behind it. | 106Β Β±5Coding IQ 105.7, 95% interval 101β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50cache read $0.05 | $3.00cache write $0.625 | 984K | 38.6Poor value (38.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 44 Β±12Terse (44 Β±12). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 148.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.6 Plus Inference by Alibaba Cloudπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 129.4From 256 benchmarks. Plenty of data behind it. | 106Β Β±5Coding IQ 105.7, 95% interval 101β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50cache read $0.05 | $3.00cache write $0.625 | βNot published by the provider | 38.6Poor value (38.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 44 Β±12Terse (44 Β±12). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 148.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen 3.8 27B 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. | 129.4From 251 benchmarks. Plenty of data behind it. | 111Β Β±7Coding IQ 111.4, 95% interval 104β119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.08cache read $0.05 | $0.35 | 1M | 39.7Poor value (39.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 152.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen 3.8 27B Inference by Alibaba Cloudπ¨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. | 129.4From 251 benchmarks. Plenty of data behind it. | 111Β Β±7Coding IQ 111.4, 95% interval 104β119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50cache read $0.10 | $3.00cache write $0.625 | βNot published by the provider | 39.7Poor value (39.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 152.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen 3.8 27B 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. | 129.4From 251 benchmarks. Plenty of data behind it. | 111Β Β±7Coding IQ 111.4, 95% interval 104β119. Plenty 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 | $2.50 | βNot published by the provider | 39.7Poor value (39.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 152.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen 3.8 27B 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. | 129.4From 251 benchmarks. Plenty of data behind it. | 111Β Β±7Coding IQ 111.4, 95% interval 104β119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.42cache read $0.085 | $3.00 | βNot published by the provider | 39.7Poor value (39.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 152.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Grok 4.20 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 129.3From 281 benchmarks. Plenty of data behind it. | 108Β Β±8Coding IQ 108.2, 95% interval 101β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $6.00 | 2M | 40.6Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 45 Β±9Typical (45 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. | 152.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Grok 4.20 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 129.3From 281 benchmarks. Plenty of data behind it. | 108Β Β±8Coding IQ 108.2, 95% interval 101β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $6.00 | 2M | 40.6Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 45 Β±9Typical (45 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. | 152.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Grok 4.20 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 129.3From 281 benchmarks. Plenty of data behind it. | 108Β Β±8Coding IQ 108.2, 95% interval 101β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.20 | $2.50 | 2M | 40.6Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 45 Β±9Typical (45 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. | 152.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Grok 4.20 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 129.3From 281 benchmarks. Plenty of data behind it. | 108Β Β±8Coding IQ 108.2, 95% interval 101β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.20 | $2.50 | 2M | 40.6Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 45 Β±9Typical (45 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. | 152.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Grok 4.20 Inference by xAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 129.3From 281 benchmarks. Plenty of data behind it. | 108Β Β±8Coding IQ 108.2, 95% interval 101β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $6.00 | βNot published by the provider | 40.6Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 45 Β±9Typical (45 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. | 152.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Grok 4.20 Inference by xAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 129.3From 281 benchmarks. Plenty of data behind it. | 108Β Β±8Coding IQ 108.2, 95% interval 101β116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $6.00 | βNot published by the provider | 40.6Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 45 Β±9Typical (45 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. | 152.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 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 | 129.1From 229 benchmarks. Plenty of data behind it. | 108Β Β±12Coding IQ 107.8, 95% interval 95β120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.076cache read $0.014 | $0.153 | 1.1M | 74.6Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 44 Β±9Terse (44 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. | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Flash Inference by Alibaba Cloudπ¨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 | 129.1From 229 benchmarks. Plenty of data behind it. | 108Β Β±12Coding IQ 107.8, 95% interval 95β120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.44cache read $0.044 | $1.32 | βNot published by the provider | 74.6Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 44 Β±9Terse (44 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. | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 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 | 129.1From 229 benchmarks. Plenty of data behind it. | 108Β Β±12Coding IQ 107.8, 95% interval 95β120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.44cache read $0.014 | $1.32 | βNot published by the provider | 74.6Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 44 Β±9Terse (44 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. | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Flash 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. Newer version | 129.1From 229 benchmarks. Plenty of data behind it. | 108Β Β±12Coding IQ 107.8, 95% interval 95β120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.09cache read $0.018 | $0.18 | βNot published by the provider | 74.6Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 44 Β±9Terse (44 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. | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Flash Inference by DeepSeekπ¨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 | 129.1From 229 benchmarks. Plenty of data behind it. | 108Β Β±12Coding IQ 107.8, 95% interval 95β120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.14cache read $0.0028 | $0.28 | βNot published by the provider | 74.6Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 44 Β±9Terse (44 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. | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Flash Inference by Fireworks 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 | 129.1From 229 benchmarks. Plenty of data behind it. | 108Β Β±12Coding IQ 107.8, 95% interval 95β120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.22cache read $0.007 | $0.66 | βNot published by the provider | 74.6Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 44 Β±9Terse (44 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. | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Flash Inference by Inference Netπ¨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 | 129.1From 229 benchmarks. Plenty of data behind it. | 108Β Β±12Coding IQ 107.8, 95% interval 95β120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.23cache read $0.0028 | $0.62 | βNot published by the provider | 74.6Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 44 Β±9Terse (44 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. | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Flash 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. Newer version | 129.1From 229 benchmarks. Plenty of data behind it. | 108Β Β±12Coding IQ 107.8, 95% interval 95β120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.14cache read $0.028 | $0.28 | βNot published by the provider | 74.6Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 44 Β±9Terse (44 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. | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Flash Inference by Together 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 | 129.1From 229 benchmarks. Plenty of data behind it. | 108Β Β±12Coding IQ 107.8, 95% interval 95β120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.14cache read $0.03 | $0.28 | βNot published by the provider | 74.6Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 44 Β±9Terse (44 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. | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Doubao Seed 2.0 Pro Newer version | 129.0From 86 benchmarks. Plenty of data behind it. | β 102Β Β±10Coding IQ 101.6, 95% interval 92β112. 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. | $0.50cache read $0.10 | $3.00 | 262K | βNot enough data yet | βNot measured | βNot measured |
GPT-5.1 Codex Inference by Microsoft AzureπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 129.0From 31 benchmarks. Plenty of data behind it. | 106Β Β±7Coding IQ 106.2, 95% interval 99β113. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25 | $10.00 | βNot published by the provider | 47.0Poor value (47.0). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 54 Β±9Typical (54 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. | βNot measured |
GPT-5.1 Codex Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 129.0From 31 benchmarks. Plenty of data behind it. | 106Β Β±7Coding IQ 106.2, 95% interval 99β113. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25 | $10.00 | βNot published by the provider | 47.0Poor value (47.0). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 54 Β±9Typical (54 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. | βNot measured |
Grok Build 0.1 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 128.7From 32 benchmarks. A fair amount of data behind it. | β 110Β Β±23Coding IQ 109.5, 95% interval 87β133. 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. | $1.00cache read $0.20 | $2.00 | 256K | 57.8Good value (57.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Grok Build 0.1 Inference by xAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 128.7From 32 benchmarks. A fair amount of data behind it. | β 110Β Β±23Coding IQ 109.5, 95% interval 87β133. 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. | $1.00cache read $0.20 | $2.00 | βNot published by the provider | 57.8Good value (57.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Kimi K2.5 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 | 128.5From 401 benchmarks. Plenty of data behind it. | 103Β Β±5Coding IQ 102.9, 95% interval 98β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.574 | $3.011 | 262K | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 Β±9Terse (42 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. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.5 Inference by Alibaba Cloudπ¨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 | 128.5From 401 benchmarks. Plenty of data behind it. | 103Β Β±5Coding IQ 102.9, 95% interval 98β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.574 | $3.011 | βNot published by the provider | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 Β±9Terse (42 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. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.5 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. Newer version | 128.5From 401 benchmarks. Plenty of data behind it. | 103Β Β±5Coding IQ 102.9, 95% interval 98β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.45cache read $0.07 | $2.25 | βNot published by the provider | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 Β±9Terse (42 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. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.5 Inference by Moonshot 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 | 128.5From 401 benchmarks. Plenty of data behind it. | 103Β Β±5Coding IQ 102.9, 95% interval 98β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.10 | $3.00 | βNot published by the provider | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 Β±9Terse (42 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. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.5 Inference by Nebius AI Studioπ¨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 | 128.5From 401 benchmarks. Plenty of data behind it. | 103Β Β±5Coding IQ 102.9, 95% interval 98β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50cache read $0.02 | $2.50 | βNot published by the provider | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 Β±9Terse (42 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. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.5 Inference by Together 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 | 128.5From 401 benchmarks. Plenty of data behind it. | 103Β Β±5Coding IQ 102.9, 95% interval 98β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50 | $2.80 | βNot published by the provider | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 Β±9Terse (42 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. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.7 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 128.4From 15 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.03cache read $0.006 | $0.13cache write $0.0375 | 984K | βNot enough data yet | βNot measured | βNot measured |
Qwen3.7 Flash Inference by Alibaba Cloudπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 128.4From 15 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.03cache read $0.006 | $0.13cache write $0.0375 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Gemma 4 31B 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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102Β Β±7Coding IQ 101.7, 95% interval 94β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.01 | $0.25 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty 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. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by CerebrasπΊπΈMaker 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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102Β Β±7Coding IQ 101.7, 95% interval 94β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.99 | $1.49 | βNot published by the provider | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty 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. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by DeepInfraπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 128.3From 333 benchmarks. Plenty of data behind it. | 102Β Β±7Coding IQ 101.7, 95% interval 94β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.20 | $0.40 | βNot published by the provider | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty 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. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Novita 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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102Β Β±7Coding IQ 101.7, 95% interval 94β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.14 | $0.40 | βNot published by the provider | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty 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. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Together 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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102Β Β±7Coding IQ 101.7, 95% interval 94β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.39 | $0.97 | βNot published by the provider | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty 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. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Muse Glimmer 30B 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. | 128.3From 58 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.30cache read $0.04 | $1.20 | 131K | 51.7Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Muse Glimmer 30B 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. | 128.3From 58 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.30cache read $0.04 | $1.20 | βNot published by the provider | 51.7Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Muse Glimmer 30B Inference by Together 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. | 128.3From 58 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.35cache read $0.04 | $1.50 | βNot published by the provider | 51.7Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
OpenAI o3 Inference by Microsoft AzureπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 128.3From 343 benchmarks. Plenty of data behind it. | 100Β Β±6Coding IQ 99.6, 95% interval 93β106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.50 | $8.00 | βNot published by the provider | 54.5Good value (54.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 58 Β±9Chatty (58 Β±9). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
OpenAI o3 Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 128.3From 343 benchmarks. Plenty of data behind it. | 100Β Β±6Coding IQ 99.6, 95% interval 93β106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.50 | $8.00 | βNot published by the provider | 54.5Good value (54.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 58 Β±9Chatty (58 Β±9). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.4 mini πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 128.1From 307 benchmarks. Plenty of data behind it. | 104Β Β±5Coding IQ 104.3, 95% interval 99β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.75cache read $0.075 | $4.50 | 400K | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 46 Β±18Typical (46 Β±18). 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. | 149.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.4 mini Inference by Microsoft AzureπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 128.1From 307 benchmarks. Plenty of data behind it. | 104Β Β±5Coding IQ 104.3, 95% interval 99β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.75cache read $0.075 | $4.50 | βNot published by the provider | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 46 Β±18Typical (46 Β±18). 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. | 149.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.4 mini Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 128.1From 307 benchmarks. Plenty of data behind it. | 104Β Β±5Coding IQ 104.3, 95% interval 99β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.75cache read $0.075 | $4.50 | βNot published by the provider | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 46 Β±18Typical (46 Β±18). 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. | 149.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)