Measured over the last 30 days
- Models Tracked
- 9
- Avg Tokens / Second
- 40.40
- Avg Time to First Token (ms)
- 1946.67
- Last Updated
- Oct 17, 2026
All baseten models
9 live · one row per model · fastest first · 3 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 |
| Beam 1.0 501B A23B | 60.00 | 60.00 | 60.00 | 880.00 |
| GLM 5.3 | 47.60 | 15.50 | 55.90 | 1130.00 |
| gpt-oss-120b | 44.00 | 21.80 | 71.60 | 1260.00 |
| GLM 5.2 | 43.80 | 6.71 | 64.10 | 1650.00 |
| Nemotron 3 Ultra | 33.10 | 33.10 | 33.10 | 1610.00 |
| DeepSeek V4 Flash 0731 | 26.40 | 26.40 | 26.40 | 2160.00 |
| Muse Spark Open | 22.80 | 10.50 | 43.10 | 3670.00 |
| DeepSeek V4.1 Flash | 16.70 | 9.33 | 24.00 | 4620.00 |
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 1279 individual prompts measured across 1185 monitoring runs over the past month.