Measured over the last 30 days
- Models Tracked
- 5
- Avg Tokens / Second
- 12.70
- Avg Time to First Token (ms)
- 12988.59
- Last Updated
- Sep 1, 2026
All sail-research models
5 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | 49.50 | 41.50 | 57.50 | 860.00 |
| DeepSeek V4 Flash 0423 | 31.10 | 23.20 | 40.40 | 870.00 |
| GLM 5.2 | 14.90 | 3.17 | 24.10 | 7410.00 |
| Kimi K2.6 | 3.73 | 2.67 | 5.43 | 17100.00 |
| DeepSeek V4 Flash 0731 | 2.89 | 1.58 | 4.09 | 20400.00 |
Frequently Asked Questions
Which sail-research model is fastest?
Based on recent tests, DeepSeek V4 Pro 0813 shows the highest average throughput among tracked sail-research models.
How many recent measurements feed this dashboard?
This provider summary aggregates 942 individual prompts measured across 762 monitoring runs over the past month.