llm-benchmarks
githubdrose.io

~anthropic/claude-sonnet-latest Benchmarks


Measured on openrouter

4 runs
Avg Tokens / Second
21.20
Avg Time to First Token (ms)
2060.00
Runs Analysed
4
Last Updated
Aug 16, 2026, 06:57 PM

Throughput distribution

Throughput over time

~anthropic/claude-sonnet-latestopenrouter0tok/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 1 tok/s (99th percentile) · dashed rule is the model's own mean · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
openrouter~anthropic/claude-sonnet-latest21.2020.1021.602060.00

Frequently Asked Questions

How fast is ~anthropic/claude-sonnet-latest?
The latest rolling average throughput is 21.20 tokens per second with an average time to first token of 2060.00 ms across 4 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 16, 2026, 06:57 PM.

Related models