XJY APIapi.xinjianya.top
Leaderboard
Model performance rankings based on speed test results. Compare models across different providers and endpoints.
Average tokens generated per second. Higher is better for fast responses.
| Rank | Provider | Model | Throughput | Avg first token latency | Total Tests |
|---|---|---|---|---|---|
| 1 | jimmy | 101506.95 t/s Best: 145658.50Worst: 13204.57 | 0.59s | 5 | |
| 2 | jimmy | 86213.91 t/s Best: 138352.88Worst: 42053.25 | 0.58s | 10 | |
| 3 |
XJY APIapi.xinjianya.top |
| grok-imagine-1.0-fast |
4998.02 t/s Best: 7933.91Worst: 1462.69 |
4.80s |
| 15 |
| 4 | XJY APIapi.xinjianya.top | nvidia/nemotron-3-nano-30b-a3b | 246.87 t/s Best: 299.20Worst: 195.73 | 1.15s | 5 |
| 5 | XJY APIapi.xinjianya.top | grok-4.1-fast | 99.38 t/s Best: 128.20Worst: 82.86 | 1.37s | 5 |
| 6 | A AI Toolsplatform.aitools.cfd | qwen/qwen2.5-7b | 90.28 t/s Best: 110.81Worst: 36.90 | 0.92s | 5 |
| 7 | XJY APIapi.xinjianya.top | grok-4.1-mini | 73.19 t/s Best: 102.55Worst: 53.30 | 7.00s | 5 |
| 8 | a api.amethyst.ltdapi.amethyst.ltd | qwen-3.5-plus | 55.05 t/s Best: 65.34Worst: 42.13 | 3.10s | 5 |
| 9 | XJY APIapi.xinjianya.top | grok-4.1-expert | 33.09 t/s Best: 53.89Worst: 16.09 | 1.05s | 5 |
| 10 | A AI Toolsplatform.aitools.cfd | zhipu/glm-4-flash | 30.82 t/s Best: 38.45Worst: 22.97 | 0.86s | 30 |
| 11 | 云 云智APIyunzhiapi.cn | Mimo-v2-Flash | 0.00 t/s Best: 0.00Worst: 0.00 | 1.16s | 45 |