Listings
All listings: Alibaba Cloud
Every listing for the models on page 1 of 10 of Alibaba Cloud, including each model's other versions and routes. Back to Alibaba Cloud
Sold by Alibaba Cloud
30 listings on this page sold by Alibaba Cloud.
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 |
|---|---|---|---|---|---|---|---|---|
Qwen4 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 144.9From 40 benchmarks. Plenty of data behind it. | β 124Β Β±12Coding IQ 124.3, 95% interval 112β137. 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. | $1.50cache read $0.075 | $4.50cache write $1.875 | 992K | 61.7Good value (61.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured |
Kimi K3.1 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. π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 142.7From 161 benchmarks. Plenty of data behind it. | 131Β Β±10Coding IQ 131.3, 95% interval 121β141. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.837 | $9.611 | βNot published by the provider | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 161.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4.1 Flash 1017 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. π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 139.7From 97 benchmarks. Plenty of data behind it. | 127Β Β±8Coding IQ 126.8, 95% interval 119β135. 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 | 71.4Good value (71.4). Cheaper per task than 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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K3 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 versionπ―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 139.2From 417 benchmarks. Plenty of data behind it. | 124Β Β±7Coding IQ 123.8, 95% interval 117β131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.827cache read $0.30 | $14.133 | 1M | 60.2Good value (60.2). Cheaper per task than 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 max effort. Little data behind it, so treat it as a rough estimate. | 158.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00cache write $2.50 | 992K | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer versionqwen3.8-max-0902 Β· 0902 Β· πΈπ¬π¨π³+3 ap-southeast-1, cn-beijing +3qwen3.8-max-0902 Β· 0902 Β· πΈπ¬π¨π³+3 ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00 | $6.00 | βNot published by the provider | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5.3 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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121Β Β±9Coding IQ 121.0, 95% interval 112β130. 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 | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 Β±10Chatty (65 Β±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4.1 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. πΈπ¬π¨π³+1 ap-southeast-1, cn-beijing +1πΈπ¬π¨π³+1 ap-southeast-1, cn-beijing, us-east-1 | 137.7From 179 benchmarks. Plenty of data behind it. | 125Β Β±16Coding IQ 124.7, 95% interval 109β140. 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 | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 Β±9Chatty (60 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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.8 Omni Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. πΈπ¬π¨π³+1 ap-southeast-1, cn-beijing +1πΈπ¬π¨π³+1 ap-southeast-1, cn-beijing, us-east-1 | 137.6From 33 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.15cache read $0.016 | $0.47 | 992K | βNot enough data yet | βNot measured | βNot measured |
DeepSeek V4 Pro 0813 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. π―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1 +3π―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, us-east-1 | 136.8From 147 benchmarks. Plenty of data behind it. | 117Β Β±7Coding IQ 117.1, 95% interval 110β124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.32 | $3.96 | βNot published by the provider | 52.5Fair value (52.5). Costs per task about what 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 default effort. Little data behind it, so treat it as a rough estimate. | 156Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.8 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 135.9From 44 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15cache read $0.016 | $0.47cache write $0.20 | 992K | 65.8Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured |
Qwen3.7 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer versionπ―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 134.9From 225 benchmarks. Plenty of data behind it. | 112Β Β±5Coding IQ 112.2, 95% interval 107β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.50cache read $0.50 | $7.50cache write $3.125 | 992K | 44.2Poor value (44.2). Costs more per task than 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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.7 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 134.9From 225 benchmarks. Plenty of data behind it. | 112Β Β±5Coding IQ 112.2, 95% interval 107β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.50 | $7.50 | βNot published by the provider | 44.2Poor value (44.2). Costs more per task than 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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.7 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer versionqwen3.7-max-2026-05-20 Β· 2026-05-20 Β· π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4qwen3.7-max-2026-05-20 Β· 2026-05-20 Β· π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 134.9From 225 benchmarks. Plenty of data behind it. | 112Β Β±5Coding IQ 112.2, 95% interval 107β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.50 | $7.50 | βNot published by the provider | 44.2Poor value (44.2). Costs more per task than 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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.7 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer versionqwen3.7-max-2026-06-08 Β· 2026-06-08 Β· πΈπ¬π¨π³+3 ap-southeast-1, cn-beijing +3qwen3.7-max-2026-06-08 Β· 2026-06-08 Β· πΈπ¬π¨π³+3 ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 134.9From 225 benchmarks. Plenty of data behind it. | 112Β Β±5Coding IQ 112.2, 95% interval 107β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.50 | $7.50 | βNot published by the provider | 44.2Poor value (44.2). Costs more per task than 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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5.2 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer versionfp8 Β· π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4fp8 Β· π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 133.9From 361 benchmarks. Plenty of data behind it. | 113Β Β±9Coding IQ 113.3, 95% interval 105β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.28 | $4.40 | 1M | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 Β±10Chatty (58 Β±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.6 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 | 132.6From 305 benchmarks. Plenty of data behind it. | 113Β Β±7Coding IQ 112.9, 95% interval 106β119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.8939 | $3.7131 | βNot published by the provider | 50.4Fair value (50.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 48 Β±14Typical (48 Β±14). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 151.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4 Flash 0731 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 versionπ―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 132.2From 149 benchmarks. Plenty of data behind it. | 113Β Β±8Coding IQ 112.8, 95% interval 105β121. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.44cache read $0.04 | $1.32 | 1M | 64.8Good value (64.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 Β±9Chatty (57 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. | 154.4Epoch 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 versionfp8 Β· π―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1 +3fp8 Β· π―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1, cn-beijing, eu-central-1, us-east-1 | 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 | 203K | 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 |
Qwen3.6 Max Preview π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 130.8From 99 benchmarks. Plenty of data behind it. | β 109Β Β±8Coding IQ 109.3, 95% interval 102β117. 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. | $1.30cache read $0.13 | $7.80cache write $1.625 | 262K | 41.5Poor value (41.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | βNot measured | 149.9Epoch 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. π―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1 +3π―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1, cn-beijing, eu-central-1, us-east-1 | 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. | $2.40cache read $0.20 | $4.80 | 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 |
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. πΈπ¬π¨π³+2 ap-southeast-1, cn-beijing +2πΈπ¬π¨π³+2 ap-southeast-1, cn-beijing, eu-central-1, us-east-1 | 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 |
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 | |
Qwen3.7 Plus π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 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 | 992K | 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 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. qwen3.7-plus-2026-05-26 Β· 2026-05-26 Β· π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1 +4qwen3.7-plus-2026-05-26 Β· 2026-05-26 Β· π―π΅πΈπ¬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1 | 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. | $0.40 | $1.60 | 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 versionπ―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1 +3π―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1 | 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 | 1M | 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 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer versionqwen3.6-plus-2026-04-02 Β· 2026-04-02 Β· π―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1 +3qwen3.6-plus-2026-04-02 Β· 2026-04-02 Β· π―π΅πΈπ¬+3 ap-northeast-1, ap-southeast-1, cn-beijing, eu-central-1, us-east-1 | 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. | $0.50 | $3.00 | 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. | $0.50 | $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 |
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. | $0.20cache read $0.04 | $0.40 | 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 |
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 versionπ―π΅π¨π³+2 ap-northeast-1, cn-beijing +2π―π΅π¨π³+2 ap-northeast-1, cn-beijing, eu-central-1, us-east-1 | 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 |
Run by Alibaba Cloud
101 listings on this page where Alibaba Cloud runs the model. Another provider sells these listings.
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 | Provider | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Yap | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|---|---|
Qwen4 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | 144.9From 40 benchmarks. Plenty of data behind it. | β 124Β Β±12Coding IQ 124.3, 95% interval 112β137. 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. | $1.50cache read $0.075 | $4.50cache write $1.875 | 1M | 61.7Good value (61.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured | |
Qwen4 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | 144.9From 40 benchmarks. Plenty of data behind it. | β 124Β Β±12Coding IQ 124.3, 95% interval 112β137. 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. | $1.50cache read $0.075 | $4.50cache write $1.875 | βNot published by the provider | 61.7Good value (61.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured | |
Qwen4 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | 144.9From 40 benchmarks. Plenty of data behind it. | β 124Β Β±12Coding IQ 124.3, 95% interval 112β137. 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. | $1.575cache read $0.0788 | $4.725 | βNot published by the provider | 61.7Good value (61.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured | |
Qwen4 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | 144.9From 40 benchmarks. Plenty of data behind it. | β 124Β Β±12Coding IQ 124.3, 95% interval 112β137. 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. | $1.575cache read $0.0788 | $4.725 | βNot published by the provider | 61.7Good value (61.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured | |
Qwen4 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | 144.9From 40 benchmarks. Plenty of data behind it. | β 124Β Β±12Coding IQ 124.3, 95% interval 112β137. 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. | $1.425cache read $0.0713 | $4.275cache write $1.7813 | 1M | 61.7Good value (61.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | βNot measured | βNot measured | |
Kimi K3.1 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. | 142.7From 161 benchmarks. Plenty of data behind it. | 131Β Β±10Coding IQ 131.3, 95% interval 121β141. 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 | $10.00 | βNot published by the provider | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 161.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K3.1 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. | 142.7From 161 benchmarks. Plenty of data behind it. | 131Β Β±10Coding IQ 131.3, 95% interval 121β141. 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 | $10.00 | 1M | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 161.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K3.1 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. | 142.7From 161 benchmarks. Plenty of data behind it. | 131Β Β±10Coding IQ 131.3, 95% interval 121β141. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $4.00cache read $0.20 | $20.00 | 1M | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 51 Β±9Typical (51 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 161.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127Β Β±8Coding IQ 126.8, 95% interval 119β135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.003 | $0.60 | 1M | 71.4Good value (71.4). Cheaper per task than 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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127Β Β±8Coding IQ 126.8, 95% interval 119β135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.006 | $1.20 | βNot published by the provider | 71.4Good value (71.4). Cheaper per task than 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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127Β Β±8Coding IQ 126.8, 95% interval 119β135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.006 | $1.20 | βNot published by the provider | 71.4Good value (71.4). Cheaper per task than 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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127Β Β±8Coding IQ 126.8, 95% interval 119β135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.189cache read $0.0038 | $0.756 | βNot published by the provider | 71.4Good value (71.4). Cheaper per task than 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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127Β Β±8Coding IQ 126.8, 95% interval 119β135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.189cache read $0.0038 | $0.756 | βNot published by the provider | 71.4Good value (71.4). Cheaper per task than 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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127Β Β±8Coding IQ 126.8, 95% interval 119β135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.18cache read $0.0036 | $0.72 | 1M | 71.4Good value (71.4). Cheaper per task than 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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K3 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 | 139.2From 417 benchmarks. Plenty of data behind it. | 124Β Β±7Coding IQ 123.8, 95% interval 117β131. 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 | $15.00 | βNot published by the provider | 60.2Good value (60.2). Cheaper per task than 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 max effort. Little data behind it, so treat it as a rough estimate. | 158.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K3 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 | 139.2From 417 benchmarks. Plenty of data behind it. | 124Β Β±7Coding IQ 123.8, 95% interval 117β131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.15cache read $0.315 | $15.75 | βNot published by the provider | 60.2Good value (60.2). Cheaper per task than 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 max effort. Little data behind it, so treat it as a rough estimate. | 158.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K3 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 | 139.2From 417 benchmarks. Plenty of data behind it. | 124Β Β±7Coding IQ 123.8, 95% interval 117β131. 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 | $15.00 | 1M | 60.2Good value (60.2). Cheaper per task than 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 max effort. Little data behind it, so treat it as a rough estimate. | 158.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00cache write $2.50 | 1M | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00cache write $2.50 | 1M | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00cache write $2.50 | βNot published by the provider | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.10cache read $0.2625 | $6.30 | βNot published by the provider | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.10cache read $0.2625 | $6.30 | βNot published by the provider | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.10cache read $0.2625 | $6.30 | βNot published by the provider | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00cache write $2.50 | 1M | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00cache write $2.50 | 984K | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.15 | $3.45 | 246K | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00 | 984K | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117Β Β±5Coding IQ 117.2, 95% interval 112β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00cache write $2.50 | 1M | 49.2Fair value (49.2). Costs per task about what 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 max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121Β Β±9Coding IQ 121.0, 95% interval 112β130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.28 | $4.40 | βNot published by the provider | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 Β±10Chatty (65 Β±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121Β Β±9Coding IQ 121.0, 95% interval 112β130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.2495cache read $0.2499 | $3.927 | βNot published by the provider | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 Β±10Chatty (65 Β±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121Β Β±9Coding IQ 121.0, 95% interval 112β130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.2495cache read $0.2499 | $3.927 | βNot published by the provider | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 Β±10Chatty (65 Β±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121Β Β±9Coding IQ 121.0, 95% interval 112β130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.19cache read $0.238 | $3.74 | 1M | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 Β±10Chatty (65 Β±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121Β Β±9Coding IQ 121.0, 95% interval 112β130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.68cache read $0.336 | $5.28 | 1M | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 Β±10Chatty (65 Β±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.7From 179 benchmarks. Plenty of data behind it. | 125Β Β±16Coding IQ 124.7, 95% interval 109β140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.003 | $0.60 | 1M | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 Β±9Chatty (60 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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.7From 179 benchmarks. Plenty of data behind it. | 125Β Β±16Coding IQ 124.7, 95% interval 109β140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.006 | $1.20 | βNot published by the provider | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 Β±9Chatty (60 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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.7From 179 benchmarks. Plenty of data behind it. | 125Β Β±16Coding IQ 124.7, 95% interval 109β140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.189cache read $0.0038 | $0.756 | βNot published by the provider | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 Β±9Chatty (60 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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.7From 179 benchmarks. Plenty of data behind it. | 125Β Β±16Coding IQ 124.7, 95% interval 109β140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.189cache read $0.0038 | $0.756 | βNot published by the provider | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 Β±9Chatty (60 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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Omni Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.6From 33 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.15 | $0.47 | 1M | βNot enough data yet | βNot measured | βNot measured | |
Qwen3.8 Omni Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.6From 33 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.15cache read $0.016 | $0.47 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured | |
Qwen3.8 Omni Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.6From 33 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.1575cache read $0.0168 | $0.4935 | βNot published by the provider | βNot enough data yet | βNot measured | βNot measured | |
Qwen3.8 Omni Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.6From 33 benchmarks. A fair amount of data behind it. | βNot enough data yet | $0.15cache read $0.016 | $0.47 | 984K | βNot enough data yet | βNot measured | βNot measured | |
DeepSeek V4 Pro 0813 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. | 136.8From 147 benchmarks. Plenty of data behind it. | 117Β Β±7Coding IQ 117.1, 95% interval 110β124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.66cache read $0.066 | $1.98 | 1M | 52.5Fair value (52.5). Costs per task about what 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 default effort. Little data behind it, so treat it as a rough estimate. | 156Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Pro 0813 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. | 136.8From 147 benchmarks. Plenty of data behind it. | 117Β Β±7Coding IQ 117.1, 95% interval 110β124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.122cache read $0.1122 | $3.366 | 1M | 52.5Fair value (52.5). Costs per task about what 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 default effort. Little data behind it, so treat it as a rough estimate. | 156Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Pro 0813 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. | 136.8From 147 benchmarks. Plenty of data behind it. | 117Β Β±7Coding IQ 117.1, 95% interval 110β124. 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 | 1M | 52.5Fair value (52.5). Costs per task about what 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 default effort. Little data behind it, so treat it as a rough estimate. | 156Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 135.9From 44 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15cache read $0.016 | $0.47cache write $0.20 | 1M | 65.8Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured | |
Qwen3.8 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 135.9From 44 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15cache read $0.016 | $0.47cache write $0.20 | βNot published by the provider | 65.8Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured | |
Qwen3.8 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 135.9From 44 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.1575cache read $0.0168 | $0.4935 | βNot published by the provider | 65.8Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured | |
Qwen3.8 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 135.9From 44 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15cache read $0.016 | $0.47cache write $0.20 | 984K | 65.8Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured | |
Qwen3.8 Flash π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 135.9From 44 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.15cache read $0.016 | $0.47 | 984K | 65.8Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | βNot measured | βNot measured | |
Qwen3.7 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 134.9From 225 benchmarks. Plenty of data behind it. | 112Β Β±5Coding IQ 112.2, 95% interval 107β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.50cache read $0.50 | $7.50cache write $3.125 | βNot published by the provider | 44.2Poor value (44.2). Costs more per task than 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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.7 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 134.9From 225 benchmarks. Plenty of data behind it. | 112Β Β±5Coding IQ 112.2, 95% interval 107β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.625cache read $0.525 | $7.875 | βNot published by the provider | 44.2Poor value (44.2). Costs more per task than 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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.7 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 134.9From 225 benchmarks. Plenty of data behind it. | 112Β Β±5Coding IQ 112.2, 95% interval 107β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.625cache read $0.525 | $7.875 | βNot published by the provider | 44.2Poor value (44.2). Costs more per task than 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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.7 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 134.9From 225 benchmarks. Plenty of data behind it. | 112Β Β±5Coding IQ 112.2, 95% interval 107β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.475cache read $0.295 | $4.425cache write $1.8438 | 984K | 44.2Poor value (44.2). Costs more per task than 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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.7 Max π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 134.9From 225 benchmarks. Plenty of data behind it. | 112Β Β±5Coding IQ 112.2, 95% interval 107β117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.50cache read $0.25 | $7.50cache write $3.125 | 1M | 44.2Poor value (44.2). Costs more per task than 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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
133.9From 361 benchmarks. Plenty of data behind it. | 113Β Β±9Coding IQ 113.3, 95% interval 105β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.28 | $4.40 | βNot published by the provider | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 Β±10Chatty (58 Β±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
133.9From 361 benchmarks. Plenty of data behind it. | 113Β Β±9Coding IQ 113.3, 95% interval 105β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.0143cache read $0.2029 | $3.1878 | βNot published by the provider | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 Β±10Chatty (58 Β±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
GLM 5.2 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 133.9From 361 benchmarks. Plenty of data behind it. | 113Β Β±9Coding IQ 113.3, 95% interval 105β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.0143cache read $0.2029 | $3.1878 | βNot published by the provider | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 Β±10Chatty (58 Β±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
133.9From 361 benchmarks. Plenty of data behind it. | 113Β Β±9Coding IQ 113.3, 95% interval 105β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.31cache read $0.462 | $7.26 | 1M | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 Β±10Chatty (58 Β±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
133.9From 361 benchmarks. Plenty of data behind it. | 113Β Β±9Coding IQ 113.3, 95% interval 105β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.966cache read $0.1932 | $3.036 | 1M | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 Β±10Chatty (58 Β±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
133.9From 361 benchmarks. Plenty of data behind it. | 113Β Β±9Coding IQ 113.3, 95% interval 105β122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.12cache read $0.224 | $3.52 | 1M | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 Β±10Chatty (58 Β±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
DeepSeek V4 Flash 0731 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 | 132.2From 149 benchmarks. Plenty of data behind it. | 113Β Β±8Coding IQ 112.8, 95% interval 105β121. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.22cache read $0.022 | $0.66 | 1M | 64.8Good value (64.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 Β±9Chatty (57 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. | 154.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Flash 0731 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 | 132.2From 149 benchmarks. Plenty of data behind it. | 113Β Β±8Coding IQ 112.8, 95% interval 105β121. 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 | 64.8Good value (64.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 Β±9Chatty (57 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. | 154.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Flash 0731 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 | 132.2From 149 benchmarks. Plenty of data behind it. | 113Β Β±8Coding IQ 112.8, 95% interval 105β121. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.3696cache read $0.037 | $1.1088 | βNot published by the provider | 64.8Good value (64.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 Β±9Chatty (57 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. | 154.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Flash 0731 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 | 132.2From 149 benchmarks. Plenty of data behind it. | 113Β Β±8Coding IQ 112.8, 95% interval 105β121. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.3696cache read $0.037 | $1.1088 | βNot published by the provider | 64.8Good value (64.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 Β±9Chatty (57 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. | 154.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Flash 0731 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 | 132.2From 149 benchmarks. Plenty of data behind it. | 113Β Β±8Coding IQ 112.8, 95% interval 105β121. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.352cache read $0.0352 | $1.056 | 1M | 64.8Good value (64.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 Β±9Chatty (57 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. | 154.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Flash 0731 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 | 132.2From 149 benchmarks. Plenty of data behind it. | 113Β Β±8Coding IQ 112.8, 95% interval 105β121. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.374cache read $0.0374 | $1.122 | 1M | 64.8Good value (64.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 Β±9Chatty (57 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. | 154.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 0910 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. Later snapshot | β 131From 67 benchmarks. Little data behind it, so treat it as a rough estimate. | βNot enough data yet | $0.18cache read $0.0036 | $0.72 | 1M | βNot enough data yet | βNot measured | βNot measured | |
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. | $0.84cache read $0.169 | $3.38cache write $1.0563 | 200K | 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 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. | $1.40cache 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 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. | $1.3965cache read $0.2594 | $4.389 | 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 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. | $1.3965cache read $0.2594 | $4.389 | 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 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. | $1.33cache read $0.247 | $4.18 | 170K | 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. | $1.69cache read $0.13 | $3.38 | 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 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. | $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 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. | $1.416cache read $0.118 | $2.832 | 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 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. | $1.56cache read $0.13 | $3.12 | 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 | |
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 | 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 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. | $0.4095 | $2.457 | 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 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. | $0.4095 | $2.457 | 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 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. | $0.39 | $2.34 | 258K | 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 | |
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 | ||
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 | 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 | |
Qwen3.7 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. | $0.42cache read $0.084 | $1.68 | 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 | |
Qwen3.7 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. | $0.42cache read $0.084 | $1.68 | 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 | |
Qwen3.7 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. | $0.32cache read $0.064 | $1.28cache write $0.40 | 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 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. | $0.23 | $0.92 | 246K | 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 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. | $0.32cache read $0.064 | $1.28cache write $0.40 | 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 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. | $0.32cache read $0.032 | $1.28cache write $0.40 | 1M | 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 | 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 | |
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. | $0.3413 | $2.0475 | 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 | |
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. | $0.325 | $1.95cache write $0.4063 | 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 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 | 1M | 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. | $0.50cache read $0.10 | $3.00cache write $0.625 | 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 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. | $0.50cache 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 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. | $0.4463cache read $0.0893 | $2.6775 | 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 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. | $0.4463cache read $0.0893 | $2.6775 | 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 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. | $0.425cache read $0.085 | $2.55cache write $0.5313 | 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 | |
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. | $0.14cache read $0.028 | $0.28 | 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 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. | $0.44cache 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 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. | $0.189cache read $0.0038 | $0.756 | 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 | |
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 | 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 |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)