LLM
Model bahasa untuk reasoning, coding, instruksi panjang, biaya token, dan kecepatan respons.
541 model52 provider25 item / halaman
541 model cocok.
| Model | Provider | Quality | Reasoning | Coding | Math | Input | Output | Speed | TTFT | Rilis |
|---|---|---|---|---|---|---|---|---|---|---|
| Swiss AI Initiative | 100 | 25.6 | 0 | 0 | $0.10 | $0.20 | - | 0ms | - | |
| 100 | 23.7 | 1.7 | 3.3 | $0.00 | $0.00 | - | 0ms | - | ||
| 100 | 22.9 | 9.5 | 10.3 | $0.00 | $0.00 | - | 0ms | - | ||
| IBM | 100 | 26.1 | 2.4 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| IBM | 100 | 25.7 | 1.9 | 1.3 | $0.00 | $0.00 | - | 0ms | - | |
| Liquid AI | 100 | 28.9 | 0 | 0 | $0.00 | $0.00 | 442 tok/s | 1.2s | - | |
| Alibaba | 100 | 23.1 | 7.3 | 10.3 | $0.11 | $0.42 | - | 0ms | - | |
| Cohere | 100 | 30.5 | 0 | 0 | $0.00 | $0.00 | 133 tok/s | 345ms | - | |
| Meta | 61 | - | - | - | $0.60 | $1.20 | - | - | - | |
| Anthropic | 59.9 | 92.6 | 76.5 | 0 | $10.00 | $50.00 | - | 0ms | - | |
| Anthropic | 55.7 | 92 | 74.3 | 0 | $5.00 | $25.00 | 67 tok/s | 29.6s | - | |
| OpenAI | 54.8 | 93.5 | 74.9 | 0 | $5.00 | $30.00 | 63 tok/s | 20.9s | - | |
| Anthropic | 53.5 | 91.4 | 73.6 | 0 | $5.00 | $25.00 | 52 tok/s | 15.1s | - | |
| OpenAI | 53.1 | 93.2 | 71.6 | 0 | $5.00 | $30.00 | 60 tok/s | 21.3s | - | |
| OpenAI | 51.4 | 92 | 71.1 | 0 | $2.50 | $15.00 | 143 tok/s | 113.0s | - | |
| Z AI | 51.1 | 89.5 | 68.8 | 0 | $1.40 | $4.40 | 89 tok/s | 1.0s | - | |
| OpenAI | 50.4 | 92.6 | 71.5 | 0 | $5.00 | $30.00 | 56 tok/s | 5.8s | - | |
| 50.2 | 92.2 | 70.1 | 0 | $1.50 | $9.00 | 221 tok/s | 15.0s | - | ||
| Anthropic | 47.2 | 87.5 | 63 | 0 | $3.00 | $15.00 | 67 tok/s | 81.6s | - | |
| 46.5 | 94.1 | 68.8 | 0 | $2.00 | $12.00 | 136 tok/s | 21.9s | - | ||
| Alibaba | 46 | 92.3 | 66 | 0 | $2.50 | $7.50 | 198 tok/s | 1.6s | - | |
| 45.4 | 92.1 | 39.4 | 0 | $1.50 | $9.00 | 231 tok/s | 12.0s | - | ||
| MiniMax | 44.4 | 92.9 | 58.6 | 0 | $0.30 | $1.20 | 55 tok/s | 2.0s | - | |
| DeepSeek | 44.3 | 88.8 | 59.4 | 0 | $0.435 | $0.87 | 97 tok/s | 1.0s | - | |
| OpenAI | 44.3 | 91.5 | 53 | 0 | $1.75 | $14.00 | 98 tok/s | 62.5s | - | |
| Anthropic | 43.7 | 89.6 | 46.2 | 0 | $5.00 | $25.00 | 56 tok/s | 14.2s | - | |
| OpenAI | 43.5 | 91 | 60.9 | 0 | $5.00 | $30.00 | 57 tok/s | 1.8s | - | |
| Meta | 43.1 | 88.4 | 58.6 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Kimi | 42.8 | 91.1 | 56 | 0 | $0.95 | $4.00 | 50 tok/s | 1.1s | - | |
| Anthropic | 42.7 | 88.5 | 54.5 | 0 | $5.00 | $25.00 | 45 tok/s | 1.1s | - | |
| OpenAI | 42.2 | 90.3 | 88.9 | 99 | $1.75 | $14.00 | 86 tok/s | 89.2s | - | |
| Xiaomi | 42.2 | 86.6 | 60.2 | 0 | $0.435 | $0.87 | 51 tok/s | 1.7s | - | |
| Kimi | 41.9 | 89.6 | 60.8 | 0 | $0.95 | $4.00 | 53 tok/s | 1.2s | - | |
| Anthropic | 40.8 | 86.6 | 87.1 | 91.3 | $5.00 | $25.00 | 57 tok/s | 10.9s | - | |
| DeepSeek | 40.8 | 90.5 | 41.7 | 0 | $0.435 | $0.87 | 92 tok/s | 1.1s | - | |
| DeepSeek | 40.3 | 89.4 | 56.2 | 0 | $0.14 | $0.28 | 110 tok/s | 1.0s | - | |
| Xiaomi | 40.3 | 87 | 40.9 | 0 | $1.00 | $3.00 | 53 tok/s | 1.5s | - | |
| Z AI | 40.2 | 86.8 | 55.8 | 0 | $1.40 | $4.40 | 102 tok/s | 815ms | - | |
| OpenAI | 40.1 | 89.9 | 37.1 | 0 | $1.75 | $14.00 | 139 tok/s | 1.2s | - | |
| Xiaomi | 40.1 | 84.9 | 41.7 | 0 | $0.14 | $0.28 | 78 tok/s | 2.0s | - | |
| OpenAI | 40 | 87.5 | 56.1 | 0 | $0.75 | $4.50 | 180 tok/s | 6.9s | - | |
| Alibaba | 40 | 88.8 | 43.9 | 0 | $1.30 | $7.80 | 44 tok/s | 1.8s | - | |
| 39.6 | 90.8 | 91.7 | 95.7 | $2.00 | $12.00 | - | 0ms | - | ||
| Alibaba | 39.6 | 88.2 | 54.5 | 0 | $0.50 | $3.00 | 53 tok/s | 1.6s | - | |
| Z AI | 39.5 | 82 | 43.2 | 0 | $1.00 | $3.20 | 80 tok/s | 875ms | - | |
| OpenAI | 39.1 | 87.1 | 43.2 | 0 | $2.63 | $15.75 | 115 tok/s | 1.1s | - | |
| Alibaba | 39 | 90 | 55.9 | 0 | $0.40 | $1.16 | 50 tok/s | 1.7s | - | |
| OpenAI | 38.9 | 87.3 | 86.8 | 94 | $1.25 | $10.00 | 110 tok/s | 45.9s | - | |
| OpenAI | 38.2 | 81.7 | 56.1 | 0 | $0.20 | $1.25 | 171 tok/s | 3.5s | - | |
| Z AI | 38.1 | 84.7 | 33.3 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Kimi | 38.1 | 87.9 | 34.8 | 0 | $0.58 | $3.00 | 53 tok/s | 1.2s | - | |
| MiniMax | 38.1 | 87.4 | 52.6 | 0 | $0.30 | $1.20 | 45 tok/s | 1.9s | - | |
| OpenAI | 38 | 86.4 | 89.4 | 96.7 | $1.75 | $14.00 | - | 0ms | - | |
| Anthropic | 37.8 | 84 | 48.5 | 0 | $5.00 | $25.00 | 46 tok/s | 2.1s | - | |
| 37.8 | 89.8 | 90.8 | 97 | $0.50 | $3.00 | 209 tok/s | 6.2s | - | ||
| NVIDIA | 37.8 | 86.7 | 49.3 | 0 | $0.675 | $2.68 | 159 tok/s | 878ms | - | |
| xAI | 37.6 | 90.1 | 42.2 | 0 | $1.25 | $2.50 | 169 tok/s | 20.0s | - | |
| DeepSeek | 37.4 | 86.7 | 38.6 | 0 | $0.14 | $0.28 | - | 0ms | - | |
| Alibaba | 37.1 | 84.2 | 53.7 | 0 | $0.60 | $3.60 | 62 tok/s | 1.4s | - | |
| xAI | 37 | 91.1 | 37.9 | 0 | $2.00 | $6.00 | 257 tok/s | 12.0s | - | |
| xAI | 36.5 | 88.5 | 40.9 | 0 | $2.00 | $6.00 | 256 tok/s | 13.4s | - | |
| Xiaomi | 36.4 | 85.5 | 35.6 | 0 | $0.40 | $2.00 | 82 tok/s | 1.8s | - | |
| OpenAI | 36.1 | 85.4 | 84.6 | 94.3 | $1.25 | $10.00 | 106 tok/s | 95.1s | - | |
| OpenAI | 36.1 | 83.7 | 84 | 98.7 | $1.25 | $10.00 | 179 tok/s | 9.1s | - | |
| xAI | 36 | 89 | 30.3 | 0 | $1.25 | $2.50 | 166 tok/s | 17.6s | - | |
| Anthropic | 35.9 | 79.9 | 46.2 | 0 | $3.00 | $15.00 | 50 tok/s | 1.0s | - | |
| Z AI | 35.4 | 83.9 | 35.6 | 0 | $1.40 | $4.40 | 59 tok/s | 1.0s | - | |
| OpenAI | 35.4 | 76.8 | 56.5 | 0 | $5.00 | $30.00 | 55 tok/s | 836ms | - | |
| xAI | 35.4 | 84.3 | 26.5 | 0 | $1.25 | $2.50 | 148 tok/s | 4.9s | - | |
| KwaiKAT | 35.4 | 85.5 | 49.2 | 0 | $0.30 | $1.20 | 120 tok/s | 941ms | - | |
| Xiaomi | 35 | 82.8 | 34.8 | 0 | $0.00 | $0.00 | 78 tok/s | 2.1s | - | |
| 34.9 | 82.8 | 46.2 | 0 | $1.50 | $9.00 | 203 tok/s | 900ms | - | ||
| Anthropic | 34.7 | 83.4 | 71.4 | 88 | $3.00 | $15.00 | 50 tok/s | 7.5s | - | |
| Anthropic | 34.7 | 81 | 73.8 | 62.7 | $5.00 | $25.00 | 55 tok/s | 1.3s | - | |
| OpenAI | 34.7 | 86 | 84.9 | 95.7 | $1.25 | $10.00 | 188 tok/s | 4.2s | - | |
| Kimi | 34.6 | 78.8 | 37.9 | 0 | $0.95 | $4.00 | 55 tok/s | 1.2s | - | |
| Z AI | 34.5 | 80.9 | 32.6 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Anthropic | 34.3 | 79.7 | 42.4 | 0 | $3.00 | $15.00 | 48 tok/s | 1.0s | - | |
| Z AI | 33.8 | 85.9 | 89.4 | 95 | $0.60 | $2.20 | 117 tok/s | 585ms | - | |
| Alibaba | 33.8 | 85.8 | 32.6 | 0 | $0.30 | $2.40 | 85 tok/s | 1.4s | - | |
| Anthropic | 33.7 | 80.9 | 65.4 | 80.3 | $15.00 | $75.00 | 38 tok/s | 9.4s | - | |
| OpenAI | 33.7 | 84.2 | 70.3 | 91.7 | $1.25 | $10.00 | 89 tok/s | 41.3s | - | |
| MiniMax | 33.7 | 84.8 | 34.8 | 0 | $0.30 | $1.20 | 237 tok/s | 5.6s | - | |
| Alibaba | 33.7 | 89.3 | 48.2 | 0 | $0.60 | $3.60 | 51 tok/s | 1.8s | - | |
| Tencent | 33.6 | 86.7 | 34.1 | 0 | $0.123 | $0.43 | 118 tok/s | 2.4s | - | |
| OpenAI | 33.5 | 84.6 | 42.4 | 0 | $5.00 | $30.00 | - | 0ms | - | |
| DeepSeek | 33.4 | 84 | 86.2 | 92 | $0.30 | $0.45 | - | 0ms | - | |
| xAI | 33.3 | 87.7 | 81.9 | 92.7 | $5.50 | $27.50 | - | 0ms | - | |
| Xiaomi | 33.2 | 83.5 | 31.1 | 0 | $0.10 | $0.30 | 81 tok/s | 1.7s | - | |
| 33.1 | 88.7 | 85.7 | 86.7 | $2.00 | $12.00 | - | 0ms | - | ||
| OpenAI | 33 | 82.8 | 83.8 | 90.7 | $0.25 | $2.00 | 93 tok/s | 77.1s | - | |
| Kimi | 32.7 | 83.8 | 85.3 | 94.7 | $0.60 | $2.50 | 147 tok/s | 844ms | - | |
| OpenAI | 32.5 | 84.5 | 0 | 0 | $20.00 | $80.00 | 35 tok/s | 60.7s | - | |
| Z AI | 32.4 | 66.6 | 39.4 | 0 | $1.00 | $3.20 | 68 tok/s | 1.1s | - | |
| Alibaba | 32.3 | 85.7 | 45.7 | 0 | $0.40 | $3.20 | 142 tok/s | 1.2s | - | |
| Alibaba | 32 | 86.1 | 35.6 | 0 | $0.60 | $3.60 | 53 tok/s | 1.8s | - | |
| Alibaba | 31.7 | 86.1 | 24.2 | 0 | $1.20 | $6.00 | - | 0ms | - | |
| Alibaba | 31.6 | 84.1 | 41.9 | 0 | $0.248 | $1.49 | 174 tok/s | 1.4s | - | |
| MiniMax | 31.4 | 83 | 81 | 82.7 | $0.30 | $1.20 | 212 tok/s | 8.1s | - | |
| DeepSeek | 31.2 | 71.7 | 36.4 | 0 | $0.435 | $0.87 | 92 tok/s | 1.0s | - | |
| OpenAI | 31.2 | 80.8 | 76.3 | 83 | $1.25 | $10.00 | 92 tok/s | 10.7s | - | |
| Xiaomi | 31.2 | 84.6 | 86.8 | 96.3 | $0.10 | $0.30 | 82 tok/s | 1.9s | - | |
| Anthropic | 31 | 79.6 | 63.6 | 73.3 | $15.00 | $75.00 | - | 0ms | - | |
| OpenAI | 30.9 | 80.3 | 69.2 | 85 | $0.25 | $2.00 | 102 tok/s | 15.1s | - | |
| Anthropic | 30.7 | 77.7 | 65.5 | 74.3 | $3.00 | $15.00 | - | 0ms | - | |
| OpenAI | 30.6 | 81.3 | 83.6 | 91.7 | $0.25 | $2.00 | 217 tok/s | 3.5s | - | |
| xAI | 30.6 | 85.3 | 82.2 | 89.3 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 30.6 | 82.6 | 21.2 | 0 | $0.40 | $4.80 | 51 tok/s | 1.3s | - | |
| InclusionAI | 30.6 | 85.7 | 42.8 | 0 | $0.30 | $2.50 | 122 tok/s | 1.9s | - | |
| OpenAI | 30.4 | 82.7 | 80.8 | 88.3 | $2.00 | $8.00 | 166 tok/s | 5.2s | - | |
| OpenAI | 30.2 | 76.1 | 33.3 | 0 | $0.20 | $1.25 | 169 tok/s | 2.7s | - | |
| Mistral | 29.9 | 74.8 | 46.9 | 0 | $1.50 | $7.50 | 151 tok/s | 580ms | - | |
| OpenAI | 29.8 | 82.3 | 34.1 | 0 | $0.75 | $4.50 | 190 tok/s | 6.1s | - | |
| StepFun | 29.7 | 80.9 | 37.3 | 0 | $0.20 | $1.15 | 395 tok/s | 768ms | - | |
| Anthropic | 29.6 | 67.2 | 43.9 | 83.7 | $1.00 | $5.00 | 134 tok/s | 11.8s | - | |
| 29.4 | 85.7 | 43.4 | 0 | $0.00 | $0.00 | 35 tok/s | 934ms | - | ||
| Kimi | 29.4 | 78.9 | 18.9 | 0 | $0.60 | $3.00 | 47 tok/s | 1.2s | - | |
| Anthropic | 29.3 | 72.7 | 59 | 37 | $3.00 | $15.00 | 46 tok/s | 1.1s | - | |
| Cohere | 29.3 | 76.1 | 25 | 0 | $0.00 | $0.00 | 198 tok/s | 161ms | - | |
| Alibaba | 29.3 | 84.2 | 31.8 | 0 | $0.30 | $2.60 | 93 tok/s | 1.4s | - | |
| Alibaba | 29.3 | 84.5 | 26.5 | 0 | $0.25 | $2.00 | 168 tok/s | 1.2s | - | |
| Alibaba | 29.3 | 82.9 | 21.2 | 0 | $0.60 | $3.60 | 63 tok/s | 1.3s | - | |
| DeepSeek | 28.7 | 71.6 | 34.1 | 0 | $0.14 | $0.28 | 103 tok/s | 1.0s | - | |
| China Mobile | 28.4 | 82.9 | 28.8 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| KwaiKAT | 28.3 | 76.4 | 74.7 | 94.7 | $0.30 | $1.20 | 114 tok/s | 885ms | - | |
| MiniMax | 28.3 | 77.7 | 82.6 | 78.3 | $0.30 | $1.20 | 117 tok/s | 1.3s | - | |
| Anthropic | 28.2 | 0 | 0 | 0 | $15.00 | $75.00 | 38 tok/s | 1.9s | - | |
| Alibaba | 28.1 | 82.7 | 29.5 | 0 | $0.40 | $3.20 | 165 tok/s | 1.1s | - | |
| Xiaomi | 27.9 | 76.2 | 35.6 | 0 | $0.90 | $2.70 | 55 tok/s | 1.8s | - | |
| OpenAI | 27.7 | 74.8 | 37.9 | 0 | $2.63 | $15.75 | 105 tok/s | 694ms | - | |
| 27.4 | 81.2 | 79.7 | 55.7 | $0.50 | $3.00 | 50 tok/s | 974ms | - | ||
| xAI | 27.4 | 84.7 | 83.2 | 89.7 | $0.20 | $0.50 | - | 0ms | - | |
| Anthropic | 27.1 | 77.2 | 36.4 | 56.3 | $0.00 | $0.00 | - | 0ms | - | |
| 27 | 84.4 | 80.1 | 87.7 | $1.25 | $10.00 | 121 tok/s | 16.6s | - | ||
| Z AI | 26.6 | 66.4 | 56.2 | 48 | $0.60 | $2.20 | 117 tok/s | 581ms | - | |
| DeepSeek | 26.3 | 79.2 | 79.8 | 89.7 | $1.64 | $2.75 | - | 0ms | - | |
| Tencent | 26.1 | 73.2 | 31.8 | 0 | $0.123 | $0.43 | 117 tok/s | 2.4s | - | |
| InclusionAI | 26.1 | 75.2 | 31.1 | 0 | $0.30 | $2.50 | - | 0ms | - | |
| ByteDance Seed | 26 | 76.4 | 76.6 | 79.3 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 26 | 71.2 | 66.9 | 51 | $1.75 | $14.00 | 70 tok/s | 671ms | - | |
| StepFun | 26 | 82.6 | 32.6 | 0 | $0.10 | $0.30 | 178 tok/s | 1.6s | - | |
| 25.7 | 79.2 | 39.3 | 0 | $0.13 | $0.40 | - | 0ms | - | ||
| OpenAI | 25.6 | 78.4 | 85.9 | 90.7 | $1.10 | $4.40 | 192 tok/s | 19.6s | - | |
| Anthropic | 25.5 | 70.1 | 54.2 | 36.3 | $15.00 | $75.00 | - | 0ms | - | |
| Anthropic | 25.5 | 68.3 | 44.9 | 38 | $3.00 | $15.00 | - | 0ms | - | |
| StepFun | 25.5 | 83.1 | 27.3 | 0 | $0.10 | $0.30 | 185 tok/s | 1.1s | - | |
| DeepSeek | 25.4 | 79.7 | 78.9 | 87.7 | $0.275 | $0.415 | - | 0ms | - | |
| NVIDIA | 25.4 | 80 | 37.7 | 0 | $0.30 | $0.75 | 234 tok/s | 1.0s | - | |
| Inception | 25.3 | 77 | 26.5 | 0 | $0.25 | $0.75 | 1002 tok/s | 3.0s | - | |
| Z AI | 25.1 | 78 | 69.5 | 86 | $0.55 | $2.20 | 57 tok/s | 1.1s | - | |
| 25 | 82.2 | 34.7 | 0 | $0.25 | $1.50 | 327 tok/s | 4.9s | - | ||
| Alibaba | 25 | 80.6 | 28.7 | 0 | $0.10 | $0.15 | 67 tok/s | 774ms | - | |
| Alibaba | 25 | 77.6 | 53.5 | 82.3 | $1.20 | $6.00 | 48 tok/s | 1.9s | - | |
| 24.8 | 76.3 | 30.3 | 0 | $0.14 | $0.40 | 54 tok/s | 1.1s | - | ||
| xAI | 24.8 | 65.8 | 35.2 | 0 | $1.25 | $2.50 | 137 tok/s | 631ms | - | |
| DeepSeek | 24.7 | 75.1 | 59.3 | 59 | $0.50 | $1.60 | - | 0ms | - | |
| LG AI Research | 24.7 | 78.3 | 76.8 | 90.3 | $0.00 | $0.00 | - | 0ms | - | |
| Arcee AI | 24.5 | 75.2 | 22.7 | 0 | $0.235 | $0.875 | 243 tok/s | 775ms | - | |
| Alibaba | 24.2 | 81.7 | 25.8 | 0 | $0.375 | $2.25 | 180 tok/s | 1.4s | - | |
| Alibaba | 24 | 76.4 | 76.7 | 80.7 | $1.66 | $7.23 | 52 tok/s | 2.0s | - | |
| 23.8 | 79.3 | 71.3 | 78.3 | $0.00 | $0.00 | - | 0ms | - | ||
| OpenAI | 23.8 | 78.2 | 30.4 | 93.4 | $0.15 | $0.60 | 349 tok/s | 523ms | - | |
| Anthropic | 23.7 | 64.6 | 51.1 | 39 | $1.00 | $5.00 | 106 tok/s | 614ms | - | |
| Anthropic | 23.5 | 65.6 | 39.4 | 21 | $3.00 | $15.00 | - | 0ms | - | |
| Kimi | 23.5 | 76.7 | 61 | 57.3 | $0.60 | $2.50 | 26 tok/s | 1.5s | - | |
| OpenAI | 23.4 | 74.7 | 39.7 | 97 | $15.00 | $60.00 | 146 tok/s | 14.6s | - | |
| Alibaba | 23.4 | 81.9 | 10.6 | 0 | $0.25 | $2.00 | 191 tok/s | 1.3s | - | |
| Xiaomi | 23.1 | 65.6 | 40.2 | 67.7 | $0.10 | $0.30 | 83 tok/s | 3.6s | - | |
| LG AI Research | 23 | 79.4 | 20.5 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| 23 | 83.6 | 46.7 | 98 | $0.00 | $0.00 | - | 0ms | - | ||
| Z AI | 23 | 63.2 | 56.1 | 44.3 | $0.60 | $2.20 | 61 tok/s | 1.7s | - | |
| Z AI | 22.9 | 58.1 | 22 | 0 | $0.07 | $0.40 | 85 tok/s | 924ms | - | |
| xAI | 22.5 | 79.1 | 69.6 | 84.7 | $0.30 | $0.50 | 66 tok/s | 661ms | - | |
| xAI | 22.5 | 78.5 | 22 | 0 | $2.00 | $6.00 | 204 tok/s | 390ms | - | |
| 22.3 | 82.2 | 77 | 98.6 | $1.25 | $10.00 | - | 0ms | - | ||
| Alibaba | 22.3 | 79 | 78.8 | 91 | $0.40 | $2.15 | 81 tok/s | 1.2s | - | |
| DeepSeek | 22.2 | 87.1 | 89.6 | 96.7 | $0.00 | $0.00 | - | 0ms | - | |
| Multiverse Computing | 22.1 | 73.3 | 23.5 | 0 | $0.04 | $0.14 | 376 tok/s | 579ms | - | |
| 22 | 75.3 | 18.2 | 0 | $0.10 | $0.30 | 158 tok/s | 1.3s | - | ||
| Baidu | 21.9 | 77.7 | 81.2 | 85 | $0.00 | $0.00 | - | 0ms | - | |
| xAI | 21.8 | 77.6 | 16.7 | 0 | $2.00 | $6.00 | 217 tok/s | 400ms | - | |
| Amazon | 21.8 | 78.5 | 34 | 89 | $1.25 | $10.00 | 126 tok/s | 18.2s | - | |
| xAI | 21.6 | 72.7 | 65.7 | 43.3 | $0.00 | $0.00 | - | 0ms | - | |
| DeepSeek | 21.4 | 75.1 | 52.9 | 53.7 | $0.27 | $1.00 | - | 0ms | - | |
| DeepSeek | 21.3 | 73.8 | 55.4 | 57.7 | $0.275 | $0.415 | - | 0ms | - | |
| NVIDIA | 21.3 | 75.8 | 21.2 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| ServiceNow | 21.2 | 71.3 | 72.8 | 87.5 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 21.2 | 73.7 | 18.2 | 0 | $0.35 | $1.20 | 93 tok/s | 1.1s | - | |
| DeepSeek | 21 | 73.5 | 57.7 | 49.7 | $0.555 | $1.67 | - | 0ms | - | |
| Amazon | 20.9 | 76 | 66 | 89.7 | $0.30 | $2.50 | - | 0ms | - | |
| Mistral | 20.8 | 76.9 | 17.4 | 0 | $0.15 | $0.60 | 162 tok/s | 572ms | - | |
| DeepSeek | 20.7 | 77.9 | 78.4 | 89.7 | $0.59 | $1.69 | - | 0ms | - | |
| Cohere | 20.6 | 75.7 | 31.1 | 0 | $0.00 | $0.00 | 171 tok/s | 191ms | - | |
| Alibaba | 20.6 | 77.2 | 64.6 | 88.3 | $0.84 | $6.18 | 57 tok/s | 1.2s | - | |
| ServiceNow | 20.5 | 73.3 | 80.7 | 88 | $0.00 | $0.00 | - | 0ms | - | |
| Amazon | 20.5 | 81.1 | 71.1 | 94.3 | $0.30 | $2.50 | 175 tok/s | 12.1s | - | |
| OpenAI | 20.4 | 64.3 | 49.4 | 38 | $1.25 | $10.00 | 98 tok/s | 620ms | - | |
| Alibaba | 20.3 | 78.6 | 23.5 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| DeepSeek | 20.1 | 81.3 | 77 | 76 | $1.35 | $4.20 | - | 0ms | - | |
| 20.1 | 79 | 69.5 | 73.3 | $0.30 | $2.50 | 206 tok/s | 14.6s | - | ||
| 20.1 | 71.4 | 25 | 0 | $0.13 | $0.40 | 42 tok/s | 1.1s | - | ||
| Mistral | 20.1 | 73.9 | 75 | 82 | $2.00 | $5.00 | 40 tok/s | 546ms | - | |
| Alibaba | 20.1 | 77.1 | 22.6 | 0 | $0.03 | $0.15 | 29 tok/s | 480ms | - | |
| OpenAI | 19.9 | 67.6 | 78.9 | 83.7 | $0.05 | $0.40 | 172 tok/s | 76.1s | - | |
| Alibaba | 19.8 | 75.9 | 78.4 | 84.3 | $0.50 | $6.00 | 184 tok/s | 1.1s | - | |
| Z AI | 19.5 | 78.2 | 73.8 | 73.7 | $0.60 | $2.20 | 53 tok/s | 1.4s | - | |
| Amazon | 19.5 | 75.1 | 63.8 | 63.3 | $1.25 | $10.00 | 129 tok/s | 4.1s | - | |
| OpenAI | 19.4 | 66.6 | 45.7 | 34.7 | $2.00 | $8.00 | 127 tok/s | 572ms | - | |
| Kimi | 19.4 | 76.6 | 55.6 | 57 | $0.585 | $2.40 | 26 tok/s | 1.5s | - | |
| InclusionAI | 19.3 | 59.3 | 21.2 | 0 | $0.10 | $0.30 | - | 0ms | - | |
| Alibaba | 19.2 | 76.4 | 65.1 | 75 | $1.20 | $6.00 | 61 tok/s | 1.9s | - | |
| OpenAI | 19 | 67 | 76.3 | 78.3 | $0.05 | $0.40 | 165 tok/s | 36.6s | - | |
| Amazon | 19 | 76.8 | 66.3 | 88.7 | $0.30 | $2.50 | 164 tok/s | 18.1s | - | |
| OpenAI | 19 | 74.8 | 71.7 | 97.3 | $1.10 | $4.40 | 225 tok/s | 5.9s | - | |
| Alibaba | 19 | 74.2 | 8.3 | 0 | $0.10 | $0.80 | 239 tok/s | 1.1s | - | |
| OpenAI | 18.9 | 0 | 0 | 0 | $150.00 | $600.00 | - | 0ms | - | |
| 18.8 | 76.6 | 62.5 | 56.7 | $0.00 | $0.00 | - | 0ms | - | ||
| China Mobile | 18.5 | 67.6 | 18.2 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| xAI | 18.4 | 69.3 | 42.5 | 58 | $4.00 | $20.00 | - | 0ms | - | |
| OpenAI | 18.4 | 77.3 | 42.1 | 98.5 | $1.10 | $4.40 | 213 tok/s | 18.2s | - | |
| ByteDance Seed | 18.3 | 72.6 | 76.5 | 84.7 | $0.21 | $0.57 | 40 tok/s | 1.5s | - | |
| Alibaba | 18.2 | 75.3 | 52.4 | 71.7 | $0.20 | $0.825 | 68 tok/s | 1.1s | - | |
| Alibaba | 18 | 61.8 | 58.5 | 39.3 | $0.30 | $1.80 | 66 tok/s | 1.6s | - | |
| Alibaba | 17.9 | 73.3 | 73.8 | 84.7 | $0.70 | $8.40 | 95 tok/s | 1.4s | - | |
| Amazon | 17.8 | 69.8 | 46.9 | 46.7 | $0.30 | $2.50 | 167 tok/s | 5.3s | - | |
| Perplexity | 17.8 | 0 | 0 | 95.7 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 17.7 | 67.2 | 70.7 | 66.7 | $0.15 | $0.60 | 359 tok/s | 478ms | - | |
| MiniMax | 17.7 | 69.7 | 71.1 | 61 | $0.55 | $2.20 | - | 0ms | - | |
| OpenAI | 17.6 | 55.8 | 24.2 | 0 | $0.20 | $1.25 | 158 tok/s | 477ms | - | |
| 17.5 | 69.8 | 50.5 | 98.1 | $0.00 | $0.00 | - | 0ms | - | ||
| NVIDIA | 17.5 | 75.7 | 74.1 | 91 | $0.055 | $0.22 | 97 tok/s | 1.4s | - | |
| MBZUAI Institute of Foundation Models | 17.4 | 71.3 | 21 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 17.2 | 67.3 | 55.8 | 31.7 | $1.25 | $10.00 | 70 tok/s | 813ms | - | |
| LongCat | 17.2 | 63.6 | 10.6 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Naver | 17 | 61.5 | 62.9 | 59 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 17 | 0 | 34 | 92.4 | $16.50 | $66.00 | - | 0ms | - | |
| xAI | 16.9 | 63.7 | 39.9 | 34.3 | $0.00 | $0.00 | - | 0ms | - | |
| Z AI | 16.8 | 71.9 | 16 | 85.3 | $0.30 | $0.90 | 69 tok/s | 1.0s | - | |
| LG AI Research | 16.7 | 69.5 | 6.8 | 44 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 16.6 | 60.6 | 18.2 | 0 | $0.75 | $4.50 | 169 tok/s | 530ms | - | |
| Amazon | 16.6 | 69.9 | 59.2 | 56 | $0.30 | $2.50 | - | 0ms | - | |
| Z AI | 16.5 | 73.3 | 68.4 | 80.7 | $0.17 | $0.98 | 82 tok/s | 1.6s | - | |
| xAI | 16.5 | 60.6 | 40.1 | 41.3 | $0.20 | $0.50 | - | 0ms | - | |
| Korea Telecom | 16.4 | 70.1 | 65.6 | 76.7 | $0.00 | $0.00 | - | 0ms | - | |
| Amazon | 16.4 | 63.6 | 47.3 | 30.7 | $1.25 | $10.00 | 163 tok/s | 729ms | - | |
| OpenAI | 16.3 | 66.4 | 48.3 | 46.3 | $0.40 | $1.60 | 94 tok/s | 534ms | - | |
| Mistral | 16.2 | 68 | 46.5 | 38 | $0.50 | $1.50 | 60 tok/s | 657ms | - | |
| InclusionAI | 16.2 | 77.4 | 64.3 | 89.3 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 16 | 71.2 | 20.3 | 0 | $0.03 | $0.15 | 49 tok/s | 417ms | - | |
| Alibaba | 15.8 | 70.7 | 70.7 | 56.3 | $0.28 | $1.85 | 145 tok/s | 1.1s | - | |
| DeepSeek | 15.7 | 65.5 | 40.5 | 41 | $1.20 | $1.25 | - | 0ms | - | |
| Prime Intellect | 15.6 | 76.1 | 77.7 | 88 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 15.5 | 59.4 | 44.8 | 36.7 | $0.00 | $0.00 | 50 tok/s | 682ms | - | |
| Z AI | 15.5 | 45.2 | 3.8 | 0 | $0.07 | $0.40 | 159 tok/s | 1.1s | - | |
| OpenAI | 15.3 | 68.6 | 54.3 | 48.3 | $1.25 | $10.00 | 185 tok/s | 485ms | - | |
| 15.1 | 70.9 | 68.8 | 68.7 | $0.10 | $0.40 | - | 0ms | - | ||
| xAI | 15.1 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Upstage | 15.1 | 65.7 | 2.3 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 14.9 | 68.8 | 20.7 | 89.3 | $0.05 | $0.20 | 237 tok/s | 557ms | - | |
| NVIDIA | 14.9 | 46.9 | 8.3 | 0 | $0.075 | $0.30 | 295 tok/s | 571ms | - | |
| Mistral | 14.8 | 58.8 | 40.6 | 38.3 | $0.40 | $2.00 | 90 tok/s | 576ms | - | |
| MiniMax | 14.4 | 68.2 | 65.7 | 13.7 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 14.3 | 68.7 | 54.5 | 46.7 | $0.25 | $2.00 | 98 tok/s | 680ms | - | |
| OpenAI | 14.3 | 61.1 | 65.2 | 62.3 | $0.06 | $0.20 | 260 tok/s | 518ms | - | |
| Meta | 14.3 | 67.1 | 16.3 | 19.3 | $0.35 | $0.85 | 110 tok/s | 625ms | - | |
| Alibaba | 14.3 | 71.2 | 59.4 | 70.7 | $0.30 | $1.90 | 55 tok/s | 1.1s | - | |
| MBZUAI Institute of Foundation Models | 14.2 | 68.1 | 69.4 | 78.3 | $0.00 | $0.00 | - | 0ms | - | |
| 14.1 | 68.3 | 49.5 | 60.3 | $0.30 | $2.50 | 188 tok/s | 464ms | - | ||
| Upstage | 14.1 | 72.4 | 16.2 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 14 | 60.3 | 57.6 | 94.4 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 13.7 | 73.8 | 68.4 | 66.3 | $0.50 | $2.00 | 185 tok/s | 1.1s | - | |
| OpenAI | 13.6 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 13.6 | 51.6 | 40.3 | 29 | $0.19 | $0.839 | 109 tok/s | 1.4s | - | |
| Trillion Labs | 13.6 | 53.8 | 2.3 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 13.4 | 70 | 62.2 | 82 | $0.70 | $8.40 | 61 tok/s | 1.3s | - | |
| Alibaba | 13.4 | 59.3 | 63.1 | 29 | $0.66 | $1.00 | 33 tok/s | 463ms | - | |
| 13.3 | 70.1 | 24.1 | 94.4 | $0.00 | $0.00 | - | 0ms | - | ||
| Alibaba | 13.3 | 72 | 69.7 | 82.3 | $0.20 | $0.75 | 123 tok/s | 1.0s | - | |
| 13.2 | 66.1 | 11.4 | 0 | $0.10 | $0.30 | 165 tok/s | 1.5s | - | ||
| Mistral | 13.1 | 53.2 | 34.8 | 34.3 | $0.00 | $0.00 | 71 tok/s | 634ms | - | |
| 13.1 | 65.1 | 64.1 | 46.7 | $0.10 | $0.40 | - | 0ms | - | ||
| InclusionAI | 12.8 | 71.9 | 67.7 | 71.3 | $0.00 | $0.00 | - | 0ms | - | |
| Motif Technologies | 12.8 | 69.5 | 65.1 | 80.3 | $0.00 | $0.00 | - | 0ms | - | |
| Amazon | 12.7 | 56.9 | 31.7 | 17.3 | $2.50 | $12.50 | 68 tok/s | 1.1s | - | |
| DeepSeek | 12.6 | 70.8 | 61.7 | 68 | $1.68 | $4.70 | - | 0ms | - | |
| 12.5 | 57.6 | 8.3 | 0 | $0.00 | $0.00 | - | 0ms | - | ||
| Mistral | 12.5 | 67.9 | 52.7 | 40.3 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 12.5 | 57.8 | 40 | 30.3 | $0.40 | $2.00 | 49 tok/s | 567ms | - | |
| Upstage | 12.5 | 57.8 | 46.2 | 90 | $0.00 | $0.00 | - | 0ms | - | |
| Anthropic | 12.4 | 40.8 | 31.4 | 72.1 | $0.80 | $4.00 | - | 0ms | - | |
| Mistral | 12.4 | 49.2 | 33.7 | 4.7 | $0.40 | $2.00 | 52 tok/s | 585ms | - | |
| MBZUAI Institute of Foundation Models | 12.4 | 59.8 | 54.1 | 64.7 | $0.00 | $0.00 | - | 0ms | - | |
| NVIDIA | 12.4 | 74.8 | 73.7 | 76.7 | $0.10 | $0.40 | 51 tok/s | 270ms | - | |
| Mistral | 12.4 | 57.1 | 10.6 | 0 | $0.15 | $0.60 | 146 tok/s | 562ms | - | |
| Trillion Labs | 12.4 | 60.1 | 0.8 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| 12.3 | 62.3 | 33.4 | 21.7 | $0.15 | $0.60 | - | 0ms | - | ||
| OpenAI | 12.3 | 65.5 | 42.5 | 25.7 | $0.00 | $0.00 | - | 0ms | - | |
| NVIDIA | 12.2 | 64.3 | 27.7 | 54.7 | $0.00 | $0.00 | - | 0ms | - | |
| OpenBMB | 12 | 27.8 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 12 | 66.7 | 64.1 | 82.7 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 11.9 | 66.3 | 72.3 | 80.3 | $0.50 | $1.50 | 108 tok/s | 458ms | - | |
| Sarvam | 11.9 | 73.8 | 1.5 | 0 | $0.042 | $0.17 | 113 tok/s | 1.2s | - | |
| Anthropic | 11.8 | 48.9 | 19.5 | 64.1 | $15.00 | $75.00 | - | 0ms | - | |
| Mistral | 11.8 | 43.4 | 25.8 | 68.4 | $0.00 | $0.00 | - | 0ms | - | |
| 11.8 | 62.2 | 25.5 | 92.3 | $0.00 | $0.00 | - | 0ms | - | ||
| Amazon | 11.8 | 60.3 | 34.6 | 33.7 | $0.30 | $2.50 | 229 tok/s | 818ms | - | |
| 11.7 | 59.4 | 40.6 | 92.6 | $0.00 | $0.00 | - | 0ms | - | ||
| OpenBMB | 11.7 | 26.9 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Perplexity | 11.7 | 62.3 | 0 | 92.1 | $0.00 | $0.00 | - | 0ms | - | |
| 11.4 | 62.5 | 59.3 | 53.3 | $0.10 | $0.40 | 353 tok/s | 19.3s | - | ||
| OpenAI | 11.2 | 54.3 | 30.9 | 6 | $2.50 | $10.00 | 220 tok/s | 471ms | - | |
| Alibaba | 11.1 | 67.1 | 51.4 | 68.3 | $0.70 | $2.80 | 74 tok/s | 1.1s | - | |
| DeepSeek | 11 | 61.5 | 27 | 63 | $0.00 | $0.00 | - | 0ms | - | |
| Z AI | 11 | 56.6 | 41.1 | 26.3 | $0.30 | $0.90 | 66 tok/s | 1.2s | - | |
| Alibaba | 10.9 | 61.3 | 34.3 | 23.7 | $0.45 | $1.80 | 66 tok/s | 1.2s | - | |
| 10.7 | 63.6 | 21 | 91.1 | $0.00 | $0.00 | - | 0ms | - | ||
| Mistral | 10.7 | 64.1 | 51.4 | 41.3 | $0.00 | $0.00 | - | 0ms | - | |
| LG AI Research | 10.6 | 73.9 | 74.7 | 80 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 10.6 | 57.9 | 35.3 | 30.7 | $0.18 | $2.10 | 132 tok/s | 1.1s | - | |
| Amazon | 10.5 | 55.5 | 30.5 | 37 | $0.30 | $2.50 | - | 0ms | - | |
| Alibaba | 10.5 | 66.8 | 54.6 | 73 | $0.195 | $0.52 | 86 tok/s | 1.1s | - | |
| DeepSeek | 10.4 | 61.2 | 51.3 | 63.7 | $0.00 | $0.00 | - | 0ms | - | |
| DeepSeek | 10.4 | 55.7 | 35.9 | 26 | $0.40 | $0.89 | - | 0ms | - | |
| Alibaba | 10.2 | 58.7 | 35.9 | 83.5 | $1.60 | $6.40 | - | 0ms | - | |
| Alibaba | 10.2 | 45.6 | 19.7 | 0 | $0.02 | $0.10 | 49 tok/s | 410ms | - | |
| Nanbeige | 10.1 | 84.9 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 10.1 | 60.4 | 52.3 | 55.7 | $0.235 | $2.22 | 64 tok/s | 1.1s | - | |
| 10 | 58.9 | 23.6 | 87.6 | $0.00 | $0.00 | - | 0ms | - | ||
| Nous Research | 10 | 69.9 | 65.3 | 68.7 | $0.13 | $0.40 | 90 tok/s | 618ms | - | |
| Meta | 10 | 58.7 | 8.2 | 14 | $0.17 | $0.66 | 114 tok/s | 575ms | - | |
| Mistral | 10 | 57.2 | 14.6 | 30 | $0.20 | $0.20 | 101 tok/s | 452ms | - | |
| Alibaba | 10 | 69.5 | 47.6 | 72.3 | $0.20 | $0.60 | 123 tok/s | 974ms | - | |
| Upstage | 10 | 54.4 | 38.5 | 87.1 | $0.00 | $0.00 | - | 0ms | - | |
| Anthropic | 9.9 | 59.9 | 30.2 | 77.1 | $3.00 | $15.00 | - | 0ms | - | |
| DeepSeek | 9.9 | 40.2 | 26.6 | 53.7 | $0.70 | $1.05 | 36 tok/s | 472ms | - | |
| DeepSeek | 9.8 | 48.4 | 37.6 | 55.7 | $0.00 | $0.00 | - | 0ms | - | |
| TII UAE | 9.8 | 66.1 | 72.4 | 80 | $0.00 | $0.00 | - | 0ms | - | |
| InclusionAI | 9.7 | 65.7 | 58.9 | 65.3 | $0.14 | $0.57 | 83 tok/s | 1.3s | - | |
| OpenAI | 9.6 | 52.1 | 31.7 | 79.5 | $2.50 | $10.00 | 108 tok/s | 582ms | - | |
| Alibaba | 9.6 | 49.1 | 27.6 | 14 | $0.36 | $0.40 | - | 0ms | - | |
| Alibaba | 9.6 | 72.6 | 67.9 | 74 | $0.25 | $0.97 | 100 tok/s | 948ms | - | |
| Perplexity | 9.5 | 47.1 | 29.5 | 81.7 | $0.00 | $0.00 | - | 0ms | - | |
| StepFun | 9.5 | 69 | 5.3 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 9.3 | 41.4 | 25.4 | 29.3 | $0.10 | $0.30 | 62 tok/s | 583ms | - | |
| 9.3 | 43.3 | 3 | 0 | $0.00 | $0.00 | - | 0ms | - | ||
| Alibaba | 9.3 | 61.6 | 50.6 | 72.3 | $0.09 | $0.45 | 113 tok/s | 1.1s | - | |
| Perplexity | 9.3 | 57.8 | 27.5 | 74.5 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 9.2 | 55.7 | 33.7 | 91 | $0.00 | $0.00 | - | 0ms | - | |
| Z AI | 9.1 | 68.4 | 60.4 | 73 | $0.60 | $1.80 | 26 tok/s | 1.2s | - | |
| NVIDIA | 9.1 | 72.8 | 64.1 | 63.7 | $0.60 | $1.80 | 52 tok/s | 713ms | - | |
| Mistral | 9.1 | 48.6 | 29.3 | 14 | $2.00 | $6.00 | 61 tok/s | 679ms | - | |
| Mistral | 9.1 | 50.5 | 27.5 | 27 | $0.087 | $0.25 | 144 tok/s | 440ms | - | |
| Alibaba | 9.1 | 65.9 | 51.5 | 66.3 | $0.15 | $0.40 | 170 tok/s | 1.1s | - | |
| Baidu | 9 | 81.1 | 46.7 | 41.3 | $0.28 | $1.10 | - | 0ms | - | |
| Nous Research | 9 | 72.7 | 68.6 | 69.7 | $1.00 | $3.00 | 40 tok/s | 791ms | - | |
| NVIDIA | 9 | 57.2 | 69.4 | 75 | $0.20 | $0.60 | 293 tok/s | 217ms | - | |
| Upstage | 9 | 68.7 | 61.6 | 61.3 | $0.00 | $0.00 | - | 0ms | - | |
| 8.9 | 54.9 | 7.6 | 0 | $0.00 | $0.00 | - | 0ms | - | ||
| IBM | 8.9 | 48.1 | 10.4 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 8.9 | 47.1 | 11.4 | 31.7 | $0.15 | $0.15 | 129 tok/s | 440ms | - | |
| 8.8 | 53.5 | 18.5 | 87.3 | $0.00 | $0.00 | - | 0ms | - | ||
| Nous Research | 8.8 | 53.6 | 54.6 | 15.3 | $1.00 | $3.00 | 40 tok/s | 780ms | - | |
| NVIDIA | 8.8 | 51.3 | 6.8 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| NVIDIA | 8.8 | 57 | 72.4 | 69.7 | $0.04 | $0.16 | 95 tok/s | 6.0s | - | |
| Alibaba | 8.8 | 43.8 | 17.4 | 0 | $0.02 | $0.10 | 47 tok/s | 721ms | - | |
| NVIDIA | 8.7 | 48.1 | 29 | 8 | $0.10 | $0.40 | 51 tok/s | 281ms | - | |
| 8.6 | 54.2 | 17.9 | 87.3 | $0.00 | $0.00 | - | 0ms | - | ||
| OpenAI | 8.6 | 52.6 | 24.2 | 79.1 | $5.00 | $15.00 | 105 tok/s | 507ms | - | |
| MBZUAI Institute of Foundation Models | 8.6 | 54.1 | 39.3 | 35.3 | $0.00 | $0.00 | - | 0ms | - | |
| Meta | 8.6 | 49.8 | 28.8 | 7.7 | $0.58 | $0.71 | 95 tok/s | 620ms | - | |
| Mistral | 8.6 | 45.4 | 21.2 | 3.7 | $0.105 | $0.235 | 154 tok/s | 534ms | - | |
| Alibaba | 8.6 | 53.5 | 28.8 | 19.7 | $0.15 | $0.59 | 94 tok/s | 1.0s | - | |
| Kimi | 8.5 | 41.2 | 37.8 | 36.3 | $0.00 | $0.00 | - | 0ms | - | |
| Meta | 8.5 | 51.5 | 30.5 | 3 | $2.75 | $6.50 | 61 tok/s | 651ms | - | |
| NVIDIA | 8.5 | 40.8 | 49.3 | 50 | $0.00 | $0.00 | - | 0ms | - | |
| NVIDIA | 8.5 | 51.7 | 28 | 7.7 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 8.4 | 52.2 | 46.5 | 22.3 | $0.11 | $1.26 | - | 0ms | - | |
| Alibaba | 8.4 | 42.7 | 33.2 | 27.3 | $0.18 | $0.70 | 145 tok/s | 917ms | - | |
| Anthropic | 8.3 | 56 | 26 | 69.5 | $3.00 | $15.00 | - | 0ms | - | |
| Liquid AI | 8.3 | 51.3 | 4.5 | 0 | $0.00 | $0.00 | 233 tok/s | 1.7s | - | |
| Allen Institute for AI | 8.3 | 51.6 | 29.1 | 77.8 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 8.2 | 51.1 | 0 | 79.7 | $0.00 | $0.00 | - | 0ms | - | |
| InclusionAI | 8.2 | 72.5 | 62.8 | 83.7 | $0.14 | $0.57 | - | 0ms | - | |
| Allen Institute for AI | 8.1 | 59.1 | 69.5 | 77.3 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 8.1 | 50.5 | 26.1 | 2.3 | $2.00 | $6.00 | 61 tok/s | 653ms | - | |
| 8 | 46.3 | 27.3 | 82.7 | $0.00 | $0.00 | - | 0ms | - | ||
| OpenAI | 8 | 42.8 | 47 | 27.3 | $0.05 | $0.40 | 166 tok/s | 624ms | - | |
| xAI | 8 | 51 | 26.7 | 77.8 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 7.9 | 3.3 | 21.5 | 73.7 | $10.00 | $30.00 | 38 tok/s | 1.4s | - | |
| Alibaba | 7.9 | 49.4 | 32 | 25.7 | $0.00 | $0.00 | - | 0ms | - | |
| Upstage | 7.8 | 56.1 | 42.4 | 30 | $0.00 | $0.00 | - | 0ms | - | |
| Cohere | 7.7 | 52.7 | 28.7 | 13 | $2.50 | $10.00 | 71 tok/s | 316ms | - | |
| Amazon | 7.7 | 49.9 | 23.3 | 7 | $0.80 | $3.20 | - | 0ms | - | |
| NVIDIA | 7.6 | 46.5 | 16.9 | 11 | $1.20 | $1.20 | 298 tok/s | 3.9s | - | |
| xAI | 7.5 | 47.1 | 24.1 | 73.7 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 7.5 | 46.6 | 24.8 | 80.5 | $0.00 | $0.00 | - | 0ms | - | |
| NVIDIA | 7.4 | 39.9 | 36 | 13.3 | $0.05 | $0.20 | 101 tok/s | 258ms | - | |
| NVIDIA | 7.4 | 55.7 | 70.1 | 62.3 | $0.05 | $0.195 | 125 tok/s | 1.3s | - | |
| Alibaba | 7.4 | 58.9 | 40.6 | 19 | $0.11 | $1.15 | 61 tok/s | 1.3s | - | |
| OpenAI | 7.3 | 51.2 | 32.6 | 24 | $0.10 | $0.40 | 192 tok/s | 514ms | - | |
| Mistral | 7.3 | 47.2 | 26.7 | 0 | $2.00 | $6.00 | - | 0ms | - | |
| Alibaba | 7.1 | 41.7 | 29.5 | 76.7 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 7.1 | 51.7 | 37.7 | 52.3 | $0.00 | $0.00 | - | 0ms | - | |
| Z AI | 7 | 57.3 | 35.2 | 15.3 | $0.60 | $1.80 | 39 tok/s | 43.3s | - | |
| OpenAI | 7 | 0 | 13.1 | 0 | $30.00 | $60.00 | 39 tok/s | 1.1s | - | |
| Alibaba | 7 | 47 | 28 | 58 | $0.235 | $0.82 | 64 tok/s | 1.1s | - | |
| 6.9 | 47.4 | 40 | 35.3 | $0.10 | $0.40 | - | 0ms | - | ||
| OpenAI | 6.9 | 42.6 | 23.4 | 14.7 | $0.15 | $0.60 | 82 tok/s | 502ms | - | |
| Nous Research | 6.9 | 49.1 | 26.9 | 11.3 | $0.13 | $0.40 | 93 tok/s | 635ms | - | |
| Mistral | 6.9 | 46.2 | 25.2 | 4.3 | $0.075 | $0.19 | 144 tok/s | 551ms | - | |
| Amazon | 6.9 | 43.3 | 16.7 | 7 | $0.06 | $0.24 | 174 tok/s | 674ms | - | |
| DeepSeek | 6.8 | 0 | 0 | 76.3 | $0.00 | $0.00 | - | 0ms | - | |
| Meta | 6.8 | 40.9 | 23.2 | 4 | $0.56 | $0.56 | 35 tok/s | 596ms | - | |
| Alibaba | 6.8 | 51.5 | 32.2 | 21.7 | $0.08 | $0.29 | 110 tok/s | 1.1s | - | |
| Alibaba | 6.8 | 39.8 | 23.3 | 84.3 | $0.11 | $0.42 | - | 0ms | - | |
| IBM | 6.7 | 43.3 | 9.5 | 0 | $0.05 | $0.10 | 124 tok/s | 469ms | - | |
| DeepSeek | 6.6 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| 6.6 | 0 | 0 | 48 | $0.00 | $0.00 | - | 0ms | - | ||
| Sarvam | 6.6 | 63.3 | 2.3 | 0 | $0.026 | $0.11 | 224 tok/s | 1.1s | - | |
| Allen Institute for AI | 6.5 | 53.9 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| DeepSeek | 6.4 | 30.2 | 23.3 | 41.3 | $0.00 | $0.00 | - | 0ms | - | |
| 6.4 | 40.5 | 2.3 | 0 | $0.00 | $0.00 | - | 0ms | - | ||
| Mistral | 6.4 | 42.4 | 0 | 67.7 | $0.00 | $0.00 | - | 0ms | - | |
| Allen Institute for AI | 6.4 | 61 | 67.2 | 73.7 | $0.00 | $0.00 | - | 0ms | - | |
| 6.3 | 37.1 | 19.8 | 67.3 | $0.00 | $0.00 | - | 0ms | - | ||
| Alibaba | 6.3 | 41 | 16.3 | 80.5 | $0.05 | $0.20 | 113 tok/s | 1.0s | - | |
| Perplexity | 6.3 | 0 | 0 | 95.4 | $0.00 | $0.00 | - | 0ms | - | |
| Reka AI | 6.3 | 0 | 0 | 52.9 | $0.20 | $0.80 | 86 tok/s | 1.7s | - | |
| Meta | 6.2 | 43.2 | 21.4 | 62.9 | $1.38 | $1.38 | 49 tok/s | 560ms | - | |
| Upstage | 6.2 | 0 | 0 | 33.1 | $0.15 | $0.15 | 64 tok/s | 817ms | - | |
| Meta | 6.1 | 25.9 | 11.6 | 4.3 | $0.10 | $0.10 | 202 tok/s | 488ms | - | |
| LG AI Research | 6 | 62.8 | 47.2 | 39.3 | $0.00 | $0.00 | - | 0ms | - | |
| xAI | 6 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 6 | 37.1 | 15.9 | 70.1 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 5.6 | 35.8 | 4.8 | 22 | $0.10 | $0.10 | 170 tok/s | 427ms | - | |
| 5.5 | 35.9 | 21.7 | 68.9 | $0.00 | $0.00 | - | 0ms | - | ||
| Nous Research | 5.3 | 38.2 | 19.5 | 59.5 | $0.00 | $0.00 | - | 0ms | - | |
| AI21 Labs | 5.3 | 39 | 18.1 | 2.3 | $2.00 | $8.00 | 59 tok/s | 894ms | - | |
| IBM | 5.2 | 41.6 | 25.1 | 13.7 | $0.06 | $0.25 | 477 tok/s | 8.7s | - | |
| DeepSeek | 5.1 | 0 | 0 | 74.3 | $0.00 | $0.00 | - | 0ms | - | |
| Nous Research | 5.1 | 40.1 | 18.8 | 53.8 | $0.30 | $0.30 | 32 tok/s | 359ms | - | |
| AI21 Labs | 5.1 | 42.7 | 14.3 | 60.6 | $2.00 | $8.00 | - | 0ms | - | |
| Alibaba | 5.1 | 45.2 | 20.2 | 24.3 | $0.18 | $0.20 | 65 tok/s | 1.4s | - | |
| Alibaba | 5.1 | 62 | 42.2 | 52.3 | $0.25 | $0.97 | 105 tok/s | 936ms | - | |
| AI21 Labs | 5 | 38.7 | 17.2 | 58 | $2.00 | $8.00 | 57 tok/s | 905ms | - | |
| Allen Institute for AI | 5 | 32.8 | 6.8 | 3.3 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 5 | 11.1 | 15 | 0 | $0.01 | $0.05 | 35 tok/s | 542ms | - | |
| 4.9 | 32.4 | 19.6 | 55.4 | $0.00 | $0.00 | - | 0ms | - | ||
| Liquid AI | 4.9 | 47.4 | 0 | 0 | $0.03 | $0.12 | 112 tok/s | 295ms | - | |
| Microsoft | 4.9 | 57.5 | 23.1 | 18 | $0.125 | $0.50 | 43 tok/s | 509ms | - | |
| 4.8 | 42.8 | 13.7 | 20.7 | $0.11 | $0.25 | - | 0ms | - | ||
| Anthropic | 4.7 | 40 | 17.5 | 41.4 | $3.00 | $15.00 | - | 0ms | - | |
| Mistral | 4.7 | 38.1 | 14.1 | 56.3 | $0.20 | $0.60 | 154 tok/s | 578ms | - | |
| Amazon | 4.7 | 35.8 | 14 | 6 | $0.035 | $0.14 | 224 tok/s | 666ms | - | |
| 4.6 | 0 | 17.6 | 0 | $0.00 | $0.00 | - | 0ms | - | ||
| 4.6 | 27.8 | 13.8 | 74.9 | $0.00 | $0.00 | - | 0ms | - | ||
| NVIDIA | 4.6 | 43.9 | 34.5 | 26.7 | $0.20 | $0.60 | 216 tok/s | 692ms | - | |
| Microsoft | 4.6 | 31.9 | 11.6 | 30 | $0.00 | $0.00 | - | 0ms | - | |
| Microsoft | 4.5 | 31.5 | 13.1 | 69.3 | $0.00 | $0.00 | 16 tok/s | 390ms | - | |
| Alibaba | 4.5 | 33.9 | 12.6 | 66 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 4.4 | 33.2 | 14.8 | 54.5 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 4.4 | 35.1 | 17.8 | 52.7 | $4.00 | $12.00 | - | 0ms | - | |
| Alibaba | 4.4 | 23.6 | 21.9 | 0 | $0.01 | $0.05 | 38 tok/s | 409ms | - | |
| Meta | 4.3 | 22.7 | 0.2 | 5.9 | $0.05 | $0.25 | 112 tok/s | 5.4s | - | |
| Meta | 4.2 | 25.5 | 8.3 | 3.3 | $0.15 | $0.15 | 53 tok/s | 604ms | - | |
| OpenBMB | 4.2 | 30.5 | 70 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| AI21 Labs | 4.1 | 33.3 | 21 | 10.7 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 4.1 | 28.9 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 4.1 | 37.1 | 29 | 37 | $0.00 | $0.00 | - | 0ms | - | |
| Reka AI | 4.1 | 52.9 | 43.5 | 33.7 | $0.20 | $0.80 | 95 tok/s | 1.9s | - | |
| Allen Institute for AI | 4 | 51.6 | 61.7 | 70.7 | $0.00 | $0.00 | - | 0ms | - | |
| Anthropic | 3.9 | 31.9 | 14 | 37.4 | $0.00 | $0.00 | - | 0ms | - | |
| Anthropic | 3.9 | 37.4 | 15.4 | 39.4 | $0.25 | $1.25 | - | 0ms | - | |
| Allen Institute for AI | 3.9 | 28.8 | 4.1 | 70 | $0.00 | $0.00 | - | 0ms | - | |
| InclusionAI | 3.8 | 56.2 | 42.9 | 49.3 | $0.00 | $0.00 | - | 0ms | - | |
| Allen Institute for AI | 3.8 | 24 | 3.9 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| DeepSeek | 3.7 | 9.8 | 7 | 22 | $0.00 | $0.00 | - | 0ms | - | |
| Anthropic | 3.6 | 34.4 | 12.9 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| DeepSeek | 3.6 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 3.6 | 29.7 | 10.7 | 44.1 | $0.50 | $1.50 | 157 tok/s | 684ms | - | |
| Mistral | 3.6 | 34.9 | 9.9 | 40.5 | $2.75 | $8.10 | 87 tok/s | 583ms | - | |
| Mistral | 3.6 | 30.2 | 11.1 | 56.2 | $1.00 | $3.00 | 151 tok/s | 569ms | - | |
| Meta | 3.5 | 37.9 | 19.8 | 48.3 | $0.65 | $2.75 | 43 tok/s | 699ms | - | |
| Snowflake | 3.4 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| 3.4 | 34.9 | 13.7 | 18.3 | $0.09 | $0.29 | - | 0ms | - | ||
| Liquid AI | 3.4 | 32.7 | 9.6 | 48 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 3.4 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Meta | 3.3 | 22.1 | 11 | 1.7 | $0.245 | $0.245 | 87 tok/s | 509ms | - | |
| IBM | 3.2 | 31.4 | 2.3 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| 3.2 | 0 | 4.6 | 0 | $0.00 | $0.00 | - | 0ms | - | ||
| DeepSeek | 3.1 | 31.9 | 15.8 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| 3.1 | 27.7 | 11.6 | 40.3 | $0.00 | $0.00 | - | 0ms | - | ||
| Cohere | 3 | 32.3 | 12.2 | 27.9 | $3.00 | $15.00 | - | 0ms | - | |
| Databricks | 3 | 33.1 | 9.3 | 27.9 | $0.00 | $0.00 | - | 0ms | - | |
| DeepSeek | 3 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Meta | 3 | 32.1 | 9.8 | 32.9 | $0.00 | $0.00 | - | 0ms | - | |
| Meta | 3 | 32.7 | 9.8 | 32.3 | $0.00 | $0.00 | - | 0ms | - | |
| OpenChat | 3 | 23 | 11.5 | 30.7 | $0.00 | $0.00 | - | 0ms | - | |
| Microsoft | 3 | 33.1 | 12.6 | 6.7 | $0.00 | $0.00 | 46 tok/s | 1.2s | - | |
| Sarvam | 3 | 41.6 | 29.5 | 84.7 | $0.00 | $0.00 | - | 0ms | - | |
| LG AI Research | 2.9 | 51.5 | 51.6 | 50.3 | $0.00 | $0.00 | - | 0ms | - | |
| LG AI Research | 2.8 | 42.4 | 29.3 | 24 | $0.00 | $0.00 | - | 0ms | - | |
| Allen Institute for AI | 2.8 | 40 | 26.6 | 41.3 | $0.10 | $0.20 | - | 0ms | - | |
| IBM | 2.7 | 26.3 | 11.5 | 6.3 | $0.00 | $0.00 | - | 0ms | - | |
| AI21 Labs | 2.7 | 30.2 | 6.2 | 35.7 | $0.20 | $0.40 | - | 0ms | - | |
| AI21 Labs | 2.7 | 32.2 | 6.1 | 30 | $0.00 | $0.00 | - | 0ms | - | |
| Liquid AI | 2.7 | 30.6 | 8.1 | 8.3 | $0.00 | $0.00 | 344 tok/s | 1.1s | - | |
| Liquid AI | 2.7 | 32.6 | 0 | 0 | $0.00 | $0.00 | 549 tok/s | 1.1s | - | |
| Liquid AI | 2.7 | 33.9 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| AI21 Labs | 2.6 | 30 | 7.1 | 25.7 | $0.20 | $0.40 | 183 tok/s | 865ms | - | |
| Alibaba | 2.6 | 35.6 | 30.8 | 38.7 | $0.11 | $1.26 | - | 0ms | - | |
| Swiss AI Initiative | 2.4 | 27.2 | 0 | 0 | $0.82 | $2.92 | - | 0ms | - | |
| 2.4 | 22.4 | 0.3 | 2.3 | $0.00 | $0.00 | - | 0ms | - | ||
| IBM | 2.4 | 33.6 | 18 | 6 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 2.4 | 29.2 | 6.6 | 29.9 | $0.45 | $0.70 | - | 0ms | - | |
| Nous Research | 2.3 | 27 | 8.5 | 21.8 | $0.00 | $0.00 | - | 0ms | - | |
| Anthropic | 2.1 | 33 | 7.8 | 26.4 | $0.00 | $0.00 | - | 0ms | - | |
| Cohere | 2.1 | 28.4 | 4.8 | 16.4 | $0.50 | $1.50 | - | 0ms | - | |
| IBM | 2.1 | 28.1 | 4.7 | 6.3 | $0.00 | $0.00 | - | 0ms | - | |
| Meta | 2.1 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Mistral | 2.1 | 17.7 | 4.6 | 12.1 | $0.20 | $0.225 | 128 tok/s | 435ms | - | |
| Alibaba | 2.1 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Allen Institute for AI | 2 | 42.5 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| IBM | 1.8 | 33.8 | 12.7 | 6.7 | $0.03 | $0.25 | 368 tok/s | 20.4s | - | |
| Liquid AI | 1.8 | 34.4 | 15.1 | 25.3 | $0.00 | $0.00 | - | 0ms | - | |
| Alibaba | 1.5 | 28.3 | 12.6 | 7.3 | $0.11 | $0.42 | - | 0ms | - | |
| Alibaba | 1.3 | 23.9 | 12.1 | 18 | $0.11 | $1.26 | - | 0ms | - | |
| 1.2 | 29.6 | 14.6 | 14.3 | $0.02 | $0.04 | 54 tok/s | 505ms | - | ||
| Meta | 1.2 | 29.6 | 9.6 | 49.9 | $0.045 | $0.145 | 82 tok/s | 501ms | - | |
| 1.1 | 29.1 | 11.2 | 12.7 | $0.04 | $0.08 | - | 0ms | - | ||
| Liquid AI | 1.1 | 22.8 | 2 | 3.3 | $0.00 | $0.00 | 566 tok/s | 1.1s | - | |
| Meta | 1.1 | 19.6 | 1.9 | 0 | $0.05 | $0.05 | 87 tok/s | 633ms | - | |
| Deep Cogito | 0 | 76.8 | 68.8 | 72.7 | $1.25 | $1.25 | 96 tok/s | 457ms | - | |
| LG AI Research | 0 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| 0 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | ||
| OpenAI | 0 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 0 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 0 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| OpenAI | 0 | 0 | 0 | 0 | $30.00 | $180.00 | - | 0ms | - | |
| OpenAI | 0 | 0 | 0 | 0 | $0.00 | $0.00 | - | 0ms | - | |
| Korea Telecom | 0 | 72.2 | 57.6 | 78.7 | $0.00 | $0.00 | - | 0ms | - |
Halaman 1



















































