llm-benchmarks
githubdrose.io

Anthropic Claude Sonnet Latest Benchmarks


Measured on claudeplatformonaws

35 runs
Avg Tokens / Second
19.90
Avg Time to First Token (ms)
2170.00
Runs Analysed
35
Last Updated
Sep 1, 2026, 02:59 AM

Throughput distribution

Throughput over time

Anthropic Claude Sonnet Latestclaudeplatformonaws1tok/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 · 1 further provider not drawn · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
claudeplatformonawsAnthropic Claude Sonnet Latest19.9017.4024.002170.00

Frequently Asked Questions

How fast is Anthropic Claude Sonnet Latest?
The latest rolling average throughput is 19.90 tokens per second with an average time to first token of 2170.00 ms across 35 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, 02:59 AM.

Related models