- Avg Tokens / Second
- 18.30
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 3180.00
- Runs Analysed
- 8
- Last Updated
- Sep 7, 2026, 08:57 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 32 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn
Every lane measuring this model
3 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 |
|---|---|---|---|---|---|---|
| anthropic | via OpenRouter | 18.30 | 9.24 | 28.20 | 3180.00 | 8 |
| anthropic | via OpenRouter · disabled | 28.90 | 11.30 | 34.50 | 1180.00 | 38 |
| anthropic | direct · disabled | 36.50 | 36.50 | 36.50 | 620.00 | 1 |
Frequently Asked Questions
How fast is Claude Sonnet 5?
The latest rolling average throughput is 18.30 tokens per second with an average time to first token of 3180.00 ms across 8 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 7, 2026, 08:57 PM.