llm-benchmarks
githubdrose.io

Claude Opus 4.1 Benchmarks


Measured on anthropic

45 runs
anthropic site
Avg Tokens / Second
15.40
Avg Time to First Token (ms)
2160.00
Runs Analysed
45
Last Updated
Aug 5, 2026, 06:45 PM

Throughput distribution

  • Claude Opus 4.1 anthropic15 tok/s
025

Visible-token throughput, same basis as the table · curves normalised per model

Throughput over time

Claude Opus 4.1anthropic1tok/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 18 tok/s (99th percentile) · dashed rule is the model's own mean

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
anthropicClaude Opus 4.115.407.2119.102160.00

Frequently Asked Questions

How fast is Claude Opus 4.1?
The latest rolling average throughput is 15.40 tokens per second with an average time to first token of 2160.00 ms across 45 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 5, 2026, 06:45 PM.