llm-benchmarks
githubdrose.io

Claude Sonnet 4.6 Benchmarks


Measured on claude-on-aws

499 runs
Avg Tokens / Second
23.30
Avg Time to First Token (ms)
1460.00
Runs Analysed
499
Last Updated
Sep 2, 2026, 03:16 AM

Throughput distribution

Throughput over time

Claude Sonnet 4.6claude-on-aws0tok/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 23 tok/s (99th percentile) · dashed rule is the model's own mean · 5 further providers not drawn · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
claude-on-awsClaude Sonnet 4.623.3021.6025.901460.00

Frequently Asked Questions

How fast is Claude Sonnet 4.6?
The latest rolling average throughput is 23.30 tokens per second with an average time to first token of 1460.00 ms across 499 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 2, 2026, 03:16 AM.

Related models