llm-benchmarks
githubdrose.io

Claude Sonnet 4.5 Benchmarks


Measured on azure

1071 runs
azure site
Avg Tokens / Second
19.20
Avg Time to First Token (ms)
1660.00
Runs Analysed
1071
Last Updated
Sep 1, 2026, 03:15 AM

Throughput distribution

Throughput over time

Claude Sonnet 4.5azure1tok/s

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 · shared vertical scale, 0 to 21 tok/s (99th percentile) · dashed rule is the model's own mean · 4 further providers not drawn

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
azureClaude Sonnet 4.519.2018.0020.501660.00

Frequently Asked Questions

How fast is Claude Sonnet 4.5?
The latest rolling average throughput is 19.20 tokens per second with an average time to first token of 1660.00 ms across 1071 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 03:15 AM.

Related models