Measured over the last 30 days
- Models Tracked
- 10
- Avg Tokens / Second
- 15.35
- Avg Time to First Token (ms)
- 6120.00
- Last Updated
- Oct 17, 2026
All baidu models
10 live · one row per model · fastest first · 4 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| GLM 5.2 | 27.70 | 17.90 | 33.10 | 1710.00 |
| GLM 5 | 25.10 | 25.10 | 25.10 | 1880.00 |
| DeepSeek V3.2 | 22.70 | 16.40 | 29.10 | 1380.00 |
| DeepSeek V4 Flash 0731 | 21.90 | 8.40 | 38.40 | 2940.00 |
| GLM 5.1 | 21.40 | 19.90 | 24.70 | 2160.00 |
| DeepSeek V4 Pro 0423 | 9.14 | 8.47 | 9.80 | 6010.00 |
| DeepSeek V4 Flash 0423 | 8.18 | 3.11 | 14.30 | 10100.00 |
| DeepSeek V4.1 Flash | 7.57 | 4.36 | 10.80 | 9820.00 |
| Kimi K2.6 | 5.63 | 1.18 | 9.92 | 11900.00 |
| DeepSeek V4 Pro 0813 | 4.23 | 4.23 | 4.23 | 13300.00 |
Frequently Asked Questions
Which baidu model is fastest?
Based on recent tests, GLM 5.2 shows the highest average throughput among tracked baidu models.
How many recent measurements feed this dashboard?
This provider summary aggregates 1682 individual prompts measured across 1590 monitoring runs over the past month.