llm-benchmarks
githubdrose.io

claude-opus-4-8 Benchmarks


Measured on anthropic

287 runs
anthropic site
Avg Tokens / Second
27.30
Avg Time to First Token (ms)
1520.00
Runs Analysed
287
Last Updated
Aug 13, 2026, 06:46 PM

Throughput distribution

Throughput over time

claude-opus-4-8anthropic8tok/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 36 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)
anthropicclaude-opus-4-827.303.8348.801520.00

Frequently Asked Questions

How fast is claude-opus-4-8?
The latest rolling average throughput is 27.30 tokens per second with an average time to first token of 1520.00 ms across 287 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 13, 2026, 06:46 PM.