Measured on alibaba
1 runs- Avg Tokens / Second
- 4.12
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 13500.00
- Runs Analysed
- 1
- Last Updated
- Oct 6, 2026, 08:01 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 58 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples
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 |
|---|---|---|---|---|---|---|
| alibaba | via OpenRouter · disabled | 4.12 | 4.12 | 4.12 | 13500.00 | 1 |
| alibaba | direct · disabled | 7.41 | 6.97 | 7.84 | 6940.00 | 2 |
Frequently Asked Questions
How fast is Qwen3 235B A22B?
The latest rolling average throughput is 4.12 tokens per second with an average time to first token of 13500.00 ms across 1 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 6, 2026, 08:01 PM.