llm-benchmarks
githubdrose.io

Claude Opus 4.6 Benchmarks


Measured on bedrock

1353 runs
Avg Tokens / Second
20.90
Avg Time to First Token (ms)
1720.00
Runs Analysed
1353
Last Updated
Aug 18, 2026, 06:10 PM

Throughput distribution

Throughput over time

Claude Opus 4.6bedrock20tok/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 25 tok/s (99th percentile) · dashed rule is the model's own mean

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
bedrockClaude Opus 4.620.903.5824.801720.00

Frequently Asked Questions

How fast is Claude Opus 4.6?
The latest rolling average throughput is 20.90 tokens per second with an average time to first token of 1720.00 ms across 1353 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 18, 2026, 06:10 PM.

Related models