Measured over the last 30 days
- Models Tracked
- 8
- Avg Tokens / Second
- 36.56
- Avg Time to First Token (ms)
- 2222.50
- Last Updated
- Oct 16, 2026
All baseten models
8 live · one row per model · fastest first · 1 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Kimi K2.7 Code | 69.20 | 69.20 | 69.20 | 540.00 |
| GLM 5.3 | 47.50 | 15.50 | 55.90 | 1140.00 |
| gpt-oss-120b | 44.40 | 21.80 | 71.60 | 1240.00 |
| GLM 5.2 | 42.80 | 6.71 | 64.10 | 1700.00 |
| Nemotron 3 Ultra | 33.10 | 33.10 | 33.10 | 1610.00 |
| DeepSeek V4 Flash 0731 | 26.40 | 26.40 | 26.40 | 2160.00 |
| DeepSeek V4.1 Flash | 16.70 | 9.33 | 24.00 | 4620.00 |
| Muse Spark Open | 12.40 | 12.40 | 12.40 | 4770.00 |
Frequently Asked Questions
Which baseten model is fastest?
Based on recent tests, Kimi K2.7 Code shows the highest average throughput among tracked baseten models.
How many recent measurements feed this dashboard?
This provider summary aggregates 1268 individual prompts measured across 1169 monitoring runs over the past month.