llm-benchmarks
githubdrose.io

claude-opus-4.5 Benchmarks


Measured on bedrock

1368 runs
Avg Tokens / Second
20.10
Avg Time to First Token (ms)
1660.00
Runs Analysed
1368
Last Updated
Aug 9, 2026, 04:37 AM

Throughput distribution

  • claude-opus-4.5 bedrock20 tok/s
025

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

Throughput over time

claude-opus-4.5bedrock20tok/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 24 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-4.520.101.0523.301660.00

Frequently Asked Questions

How fast is claude-opus-4.5?
The latest rolling average throughput is 20.10 tokens per second with an average time to first token of 1660.00 ms across 1368 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 9, 2026, 04:37 AM.

Related models