智谱AI开放平台open.bigmodel.cn
22.27 s
Best: 18.99Worst: 26.53
53.18t/s
Leaderboard
Model performance rankings based on speed test results. Compare models across different providers and endpoints.
Average time to first token. Lower is better for responsiveness.
| Rank | Provider | Model | First Token Latency | Avg tokens per second | Total Tests |
|---|---|---|---|---|---|
| 1 | claude-opus-4-5-20251101 | 2.49 s Best: 2.41Worst: 2.57 | 45.89t/s | 5 | |
| 2 | gemini-3-flash-preview | 6.26 s Best: 5.66Worst: 6.52 | 140.55t/s | 5 |
| 3 | h hiapi.onlinehiapi.online | gemini-3-pro-preview | 15.73 s Best: 13.86Worst: 18.60 | 143.36t/s | 5 |
| 4 | 智谱AI开放平台open.bigmodel.cn | GLM-4.7-FlashX | 22.27 s Best: 18.99Worst: 26.53 | 53.18t/s | 5 |