Listings
All listings: Llmgateway
Every listing for the models on page 5 of 13 of Llmgateway, including each model's other versions and routes. Back to Llmgateway
Sold by Llmgateway
78 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 |
|---|---|---|---|---|---|---|---|---|
Gemini 3.5 Flash Lite πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105Β Β±6Coding IQ 105.2, 95% interval 99β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.03 | $2.50 | 1M | 46.2Poor value (46.2). Costs more per task than 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. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.5 Flash Lite Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105Β Β±6Coding IQ 105.2, 95% interval 99β111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.03 | $2.50 | βNot published by the provider | 46.2Poor value (46.2). Costs more per task than 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. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Hy3 (Deep Infra) 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. | 127.2From 119 benchmarks. Plenty of data behind it. | 111Β Β±6Coding IQ 111.3, 95% interval 105β118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.132cache read $0.033 | $0.528 | 262K | 52.3Fair value (52.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Hy3 (Deep Infra) 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. | 127.2From 119 benchmarks. Plenty of data behind it. | 111Β Β±6Coding IQ 111.3, 95% interval 105β118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.14cache read $0.035 | $0.58 | βNot published by the provider | 52.3Fair value (52.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Hy3 (Deep Infra) 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. | 127.2From 119 benchmarks. Plenty of data behind it. | 111Β Β±6Coding IQ 111.3, 95% interval 105β118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.14cache read $0.035 | $0.58 | βNot published by the provider | 52.3Fair value (52.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
GLM 4.7 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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104Β Β±5Coding IQ 103.5, 95% interval 98β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.45 | $2.00 | 205K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 Β±9Chatty (61 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. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104Β Β±5Coding IQ 103.5, 95% interval 98β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.431 | $2.007 | βNot published by the provider | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 Β±9Chatty (61 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. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 Inference by Cerebrasπ¨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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104Β Β±5Coding IQ 103.5, 95% interval 98β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.25 | $2.75 | βNot published by the provider | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 Β±9Chatty (61 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. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104Β Β±5Coding IQ 103.5, 95% interval 98β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.11 | $2.20 | βNot published by the provider | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 Β±9Chatty (61 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. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104Β Β±5Coding IQ 103.5, 95% interval 98β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.45 | $2.00 | βNot published by the provider | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 Β±9Chatty (61 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. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104Β Β±5Coding IQ 103.5, 95% interval 98β109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.11 | $2.20 | βNot published by the provider | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 Β±9Chatty (61 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. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code 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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105Β Β±9Coding IQ 104.5, 95% interval 96β113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.737cache read $0.143 | $3.08 | 262K | 43.6Poor value (43.6). 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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code 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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105Β Β±9Coding IQ 104.5, 95% interval 96β113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.90cache read $0.38 | $8.00 | 262K | 43.6Poor value (43.6). 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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code 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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105Β Β±9Coding IQ 104.5, 95% interval 96β113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.95cache read $0.19 | $4.00 | βNot published by the provider | 43.6Poor value (43.6). 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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code 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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105Β Β±9Coding IQ 104.5, 95% interval 96β113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.95cache read $0.19 | $4.00 | βNot published by the provider | 43.6Poor value (43.6). 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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code 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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105Β Β±9Coding IQ 104.5, 95% interval 96β113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.90cache read $0.38 | $8.00 | βNot published by the provider | 43.6Poor value (43.6). 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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code 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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105Β Β±9Coding IQ 104.5, 95% interval 96β113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.95 | $4.00 | βNot published by the provider | 43.6Poor value (43.6). 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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code 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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105Β Β±9Coding IQ 104.5, 95% interval 96β113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.95cache read $0.19 | $4.00 | βNot published by the provider | 43.6Poor value (43.6). 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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5 Turbo π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 54 benchmarks. A fair amount of data behind it. | β 104Β Β±11Coding IQ 103.5, 95% interval 93β114. 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. | $1.20cache read $0.24 | $4.00 | 200K | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
GLM 5V Turbo π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 68 benchmarks. Plenty of data behind it. | 102Β Β±22Coding IQ 101.9, 95% interval 80β124. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.20cache read $0.24 | $4.00 | 200K | 52.2Fair value (52.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
MiniMax M3 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107Β Β±9Coding IQ 107.2, 95% interval 98β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.28cache read $0.056 | $1.10 | 1M | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 Β±8Chatty (71 Β±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by DeepInfraπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107Β Β±9Coding IQ 107.2, 95% interval 98β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.28cache read $0.056 | $1.10 | βNot published by the provider | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 Β±8Chatty (71 Β±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by MiniMaxπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107Β Β±9Coding IQ 107.2, 95% interval 98β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.12 | $2.40 | βNot published by the provider | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 Β±8Chatty (71 Β±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by Nebius AI Studioπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107Β Β±9Coding IQ 107.2, 95% interval 98β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30 | $1.20 | βNot published by the provider | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 Β±8Chatty (71 Β±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by Novita AIπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107Β Β±9Coding IQ 107.2, 95% interval 98β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.06 | $1.20 | βNot published by the provider | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 Β±8Chatty (71 Β±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by Together AIπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107Β Β±9Coding IQ 107.2, 95% interval 98β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.06 | $1.20 | βNot published by the provider | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 Β±8Chatty (71 Β±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.5 122B-A10B 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. | 126.7From 287 benchmarks. Plenty of data behind it. | 99Β Β±7Coding IQ 99.3, 95% interval 92β107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40 | $3.20 | 262K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Qwen3.5 122B-A10B 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. | 126.7From 287 benchmarks. Plenty of data behind it. | 99Β Β±7Coding IQ 99.3, 95% interval 92β107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40 | $3.20 | βNot published by the provider | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Qwen3.5 122B-A10B 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. | 126.7From 287 benchmarks. Plenty of data behind it. | 99Β Β±7Coding IQ 99.3, 95% interval 92β107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40 | $3.20 | βNot published by the provider | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | βNot measured |
Ling 3.0 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 | 125.6From 52 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.06cache read $0.012 | $0.18 | 262K | 64.2Good value (64.2). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Ling 3.0 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 | 125.6From 52 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.06cache read $0.012 | $0.18 | βNot published by the provider | 64.2Good value (64.2). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Ling 3.0 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 | 125.6From 52 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.06cache read $0.012 | $0.18 | βNot published by the provider | 64.2Good value (64.2). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen3.5 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. Newer version | 125.6From 331 benchmarks. Plenty of data behind it. | 101Β Β±7Coding IQ 100.7, 95% interval 94β107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30 | $2.40 | 262K | 42.4Poor value (42.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 56 Β±9Chatty (56 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. | βNot measured |
Qwen3.5 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. Newer version | 125.6From 331 benchmarks. Plenty of data behind it. | 101Β Β±7Coding IQ 100.7, 95% interval 94β107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30 | $2.40 | βNot published by the provider | 42.4Poor value (42.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 56 Β±9Chatty (56 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. | βNot measured |
Qwen3 VL Plus π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | β 125From 21 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.20cache read $0.04 | $1.60cache write $0.25 | 262K | 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 |
Qwen3 VL Plus Inference by Alibaba Cloudπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | β 125From 21 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.20cache read $0.04 | $1.60cache write $0.25 | βNot published by the provider | 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 |
Gemini 3.1 Flash Lite πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97Β Β±10Coding IQ 97.2, 95% interval 88β107. Plenty 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 | $1.50 | 1M | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Lite Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97Β Β±10Coding IQ 97.2, 95% interval 88β107. Plenty 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 | $1.50 | βNot published by the provider | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini Omni 1.1 Flash πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | β 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $1.50 | $9.00 | 131K | βNot enough data yet | βNot measured | βNot measured |
Gemini Omni 1.1 Flash πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | β 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $1.50 | $9.00 | 131K | βNot enough data yet | βNot measured | βNot measured |
Gemini Omni 1.1 Flash πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | β 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $1.50 | $9.00 | 131K | βNot enough data yet | βNot measured | βNot measured |
Gemini Omni 1.1 Flash πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | β 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $1.50 | $9.00 | 131K | βNot enough data yet | βNot measured | βNot measured |
Gemini Omni 1.1 Flash Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | β 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $1.50 | $9.00 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Gemini Omni 1.1 Flash Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | β 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $1.50 | $9.00 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Gemini Omni 1.1 Flash Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | β 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $1.50 | $9.00 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Gemini Omni 1.1 Flash Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | β 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $1.50 | $9.00 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Grok 4 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 125.2From 296 benchmarks. Plenty of data behind it. | 98Β Β±13Coding IQ 98.0, 95% interval 85β111. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00cache read $0.75 | $15.00 | 256K | 32.7Poor value (32.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Grok 4 Inference by xAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 125.2From 296 benchmarks. Plenty of data behind it. | 98Β Β±13Coding IQ 98.0, 95% interval 85β111. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00cache read $0.75 | $15.00 | βNot published by the provider | 32.7Poor value (32.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 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 | 125.0From 247 benchmarks. Plenty of data behind it. | 101Β Β±7Coding IQ 101.2, 95% interval 94β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.26cache read $0.13 | $0.38 | 164K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 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 | 125.0From 247 benchmarks. Plenty of data behind it. | 101Β Β±7Coding IQ 101.2, 95% interval 94β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.57cache read $0.114 | $1.71 | βNot published by the provider | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 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 | 125.0From 247 benchmarks. Plenty of data behind it. | 101Β Β±7Coding IQ 101.2, 95% interval 94β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.26cache read $0.13 | $0.38 | βNot published by the provider | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 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 | 125.0From 247 benchmarks. Plenty of data behind it. | 101Β Β±7Coding IQ 101.2, 95% interval 94β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.28cache read $0.028 | $0.42 | βNot published by the provider | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 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 | 125.0From 247 benchmarks. Plenty of data behind it. | 101Β Β±7Coding IQ 101.2, 95% interval 94β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30 | $0.45 | βNot published by the provider | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 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 | 125.0From 247 benchmarks. Plenty of data behind it. | 101Β Β±7Coding IQ 101.2, 95% interval 94β108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.269cache read $0.1345 | $0.40 | βNot published by the provider | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B 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. | 124.9From 216 benchmarks. Plenty of data behind it. | 102Β Β±8Coding IQ 101.7, 95% interval 94β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.067cache read $0.01 | $0.29 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount 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. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B 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. | 124.9From 216 benchmarks. Plenty of data behind it. | 102Β Β±8Coding IQ 101.7, 95% interval 94β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.07 | $0.34 | βNot published by the provider | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount 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. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B 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. | 124.9From 216 benchmarks. Plenty of data behind it. | 102Β Β±8Coding IQ 101.7, 95% interval 94β110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.13 | $0.40 | βNot published by the provider | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount 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. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 mini Inference by Microsoft AzureπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.6From 388 benchmarks. Plenty of data behind it. | 98Β Β±14Coding IQ 98.3, 95% interval 85β112. Plenty 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 | $2.00 | βNot published by the provider | 55.1Good value (55.1). 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 at default effort. Little data behind it, so treat it as a rough estimate. | 146Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 mini Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.6From 388 benchmarks. Plenty of data behind it. | 98Β Β±14Coding IQ 98.3, 95% interval 85β112. Plenty 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 | $2.00 | βNot published by the provider | 55.1Good value (55.1). 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 at default effort. Little data behind it, so treat it as a rough estimate. | 146Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Ling 3.0 Flash VL 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. | β 125From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.06cache read $0.012 | $0.18 | 131K | 65.3Good value (65.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Ling 3.0 Flash VL 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. | β 125From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.06cache read $0.012 | $0.18 | βNot published by the provider | 65.3Good value (65.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Grok 4.3 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101Β Β±8Coding IQ 101.2, 95% interval 94β109. 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 | 1M | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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 4.3 Inference by Amazon Web ServicesπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101Β Β±8Coding IQ 101.2, 95% interval 94β109. 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 | βNot published by the provider | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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 4.3 Inference by Microsoft AzureπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101Β Β±8Coding IQ 101.2, 95% interval 94β109. 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 | βNot published by the provider | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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 4.3 Inference by xAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101Β Β±8Coding IQ 101.2, 95% interval 94β109. 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 | βNot published by the provider | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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 Mini Inference by Microsoft AzureπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 123.8From 24 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.25cache read $0.025 | $2.00 | βNot published by the provider | 62.1Good value (62.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
GPT-5.1 Codex Mini Inference by OpenAIπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 123.8From 24 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.25cache read $0.025 | $2.00 | βNot published by the provider | 62.1Good value (62.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Sakana Namazu π―π΅Maker headquartered in JP, according to the company's own website. The citation is on the model page. | β 124From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.95cache read $0.15 | $4.00 | 262K | βNot enough data yet | βNot measured | βNot measured |
Sakana Namazu Inference by Sakana AIπ―π΅Maker headquartered in JP, according to the company's own website. The citation is on the model page. | β 124From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.95cache read $0.15 | $4.00 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Gemini Embedding 001 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 123.5From 68 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15 | β | 2K | βNot enough data yet | βNot measured | βNot measured |
Gemini Embedding 001 Inference by GoogleπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | 123.5From 68 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15 | β | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured |
Qwen3.6 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. Newer version | 123.4From 160 benchmarks. Plenty of data behind it. | 101Β Β±6Coding IQ 100.9, 95% interval 95β107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15 | $1.35 | 16K | 39.6Poor value (39.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | βNot measured | 146.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.6 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 | 123.1From 174 benchmarks. Plenty of data behind it. | 96Β Β±22Coding IQ 96.0, 95% interval 74β118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.55cache read $0.11 | $2.20 | 205K | 46.8Poor value (46.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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 |
GLM 4.6 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 | 123.1From 174 benchmarks. Plenty of data behind it. | 96Β Β±22Coding IQ 96.0, 95% interval 74β118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.431 | $2.007 | βNot published by the provider | 46.8Poor value (46.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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 |
GLM 4.6 Inference by Cerebrasπ¨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 | 123.1From 174 benchmarks. Plenty of data behind it. | 96Β Β±22Coding IQ 96.0, 95% interval 74β118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.25 | $2.75 | βNot published by the provider | 46.8Poor value (46.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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 |
GLM 4.6 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 | 123.1From 174 benchmarks. Plenty of data behind it. | 96Β Β±22Coding IQ 96.0, 95% interval 74β118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.55cache read $0.11 | $2.20 | βNot published by the provider | 46.8Poor value (46.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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 |
GLM 4.6 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 | 123.1From 174 benchmarks. Plenty of data behind it. | 96Β Β±22Coding IQ 96.0, 95% interval 74β118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.11 | $2.20 | βNot published by the provider | 46.8Poor value (46.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 Β±9Typical (48 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 |
Seed 2.0 Liteseed-2-0-lite-260428 Β· 260428seed-2-0-lite-260428 Β· 260428 | 123.0From 7 benchmarks. A fair amount of data behind it. | β 106Β Β±10Coding IQ 105.8, 95% interval 96β116. 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. | $0.25cache read $0.05 | $2.00 | 262K | 56.0Good value (56.0). Cheaper per task than 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)