llm-benchmarks
githubdrose.io

Claude Opus 4.7 Benchmarks


Measured on bedrock

1073 runs
Avg Tokens / Second
35.00
Decode Tokens / Second
—
Avg Time to First Token (ms)
970.00
Runs Analysed
1073
Last Updated
Nov 11, 2026, 04:00 PM

Throughput distribution

Throughput over time

Claude Opus 4.7bedrock35tok/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 · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 45 tok/s (99th percentile) · dashed rule is the model's own mean

Every lane measuring this model

1 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
bedrockdirect · disabled35.009.9946.20970.001073

Frequently Asked Questions

How fast is Claude Opus 4.7?
The latest rolling average throughput is 35.00 tokens per second with an average time to first token of 970.00 ms across 1073 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 11, 2026, 04:00 PM.

Related models