Measured over the last 30 days
- Models Tracked
- 10
- Avg Tokens / Second
- 4.15
- Avg Time to First Token (ms)
- 32832.00
- Last Updated
- Oct 16, 2026
All zai models
10 live · one row per model · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| GLM 5.2 | 17.80 | 16.90 | 18.60 | 2410.00 |
| GLM 4.5 Air | 11.20 | 9.69 | 13.10 | 5210.00 |
| GLM 4.5V | 2.22 | 2.22 | 2.22 | 26800.00 |
| GLM 5V Turbo | 1.78 | 1.78 | 1.78 | 27500.00 |
| GLM 4.5 | 1.61 | 1.61 | 1.61 | 40400.00 |
| GLM 5 Turbo | 1.61 | 1.61 | 1.61 | 37200.00 |
| GLM 4.6V | 1.60 | 1.60 | 1.60 | 36900.00 |
| GLM 5.1 | 1.33 | 1.28 | 1.38 | 45600.00 |
| GLM 4.6 | 1.31 | 1.23 | 1.38 | 49500.00 |
| GLM 4.7 | 1.02 | 1.02 | 1.02 | 56800.00 |
Frequently Asked Questions
Which zai model is fastest?
Based on recent tests, GLM 5.2 shows the highest average throughput among tracked zai models.
How many recent measurements feed this dashboard?
This provider summary aggregates 420 individual prompts measured across 418 monitoring runs over the past month.