Measured on siliconflow
5 runs- Avg Tokens / Second
- 11.20
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 2600.00
- Runs Analysed
- 5
- Last Updated
- Oct 13, 2026, 12:17 PM
Throughput distribution
Throughput over time
Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 14 tok/s (99th percentile) · dashed rule is the model's own mean
Every lane measuring this model
2 measured · live first · a lane is a provider, a catalogue id and a transport| Provider | Lane | Avg Toks/Sec | Min | Max | Avg TTF (ms) | n |
|---|---|---|---|---|---|---|
| siliconflow | direct | 11.20 | 6.59 | 13.30 | 2600.00 | 5 |
| siliconflow | via OpenRouter | 8.37 | 4.62 | 11.20 | 3040.00 | 4 |
Frequently Asked Questions
How fast is DeepSeek V3.2?
The latest rolling average throughput is 11.20 tokens per second with an average time to first token of 2600.00 ms across 5 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 13, 2026, 12:17 PM.