Measured over the last 30 days
- Models Tracked
- 13
- Avg Tokens / Second
- 12.49
- Avg Time to First Token (ms)
- 13803.28
- Last Updated
- Sep 2, 2026
All baidu models
13 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 29.30 | 13.30 | 44.20 | 2320.00 |
| GLM 5.2 | 25.50 | 23.50 | 26.80 | 1790.00 |
| DeepSeek V4 Flash 0731 | 24.80 | 17.70 | 28.30 | 2120.00 |
| GLM 5.1 | 24.50 | 2.82 | 32.30 | 2070.00 |
| GLM 5.1 | 23.60 | 21.10 | 24.50 | 1880.00 |
| DeepSeek V3.2 | 21.50 | 17.70 | 24.10 | 1380.00 |
| GLM 5.2 | 21.30 | 11.70 | 27.50 | 1630.00 |
| GLM 5.2 | 13.00 | 9.47 | 16.20 | 1660.00 |
| DeepSeek V4 Flash 0423 | 12.90 | 9.06 | 16.00 | 4830.00 |
| DeepSeek V4 Pro 0423 | 11.90 | 8.10 | 14.10 | 4370.00 |
| Kimi K2.6 | 3.61 | 2.32 | 6.08 | 19100.00 |
| GLM 5 | 2.37 | 2.17 | 2.78 | 26100.00 |
| Kimi K2.6 | 2.12 | 2.12 | 2.12 | 27700.00 |
Frequently Asked Questions
Which baidu model is fastest?
Based on recent tests, DeepSeek V4 Flash 0731 shows the highest average throughput among tracked baidu models.
How many recent measurements feed this dashboard?
This provider summary aggregates 3539 individual prompts measured across 3272 monitoring runs over the past month.