llm-benchmarks
githubdrose.io

anthropic/claude-4.7-opus-20260416 Benchmarks


Measured on openrouter

5 runs
Avg Tokens / Second
25.40
Avg Time to First Token (ms)
1660.00
Runs Analysed
5
Last Updated
Aug 16, 2026, 06:52 PM

Throughput distribution

Throughput over time

anthropic/claude-4.7-opus-20260416openrouter0tok/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 1 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)
openrouteranthropic/claude-4.7-opus-2026041625.4020.6039.401660.00

Frequently Asked Questions

How fast is anthropic/claude-4.7-opus-20260416?
The latest rolling average throughput is 25.40 tokens per second with an average time to first token of 1660.00 ms across 5 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 16, 2026, 06:52 PM.

Related models