llm-benchmarks
githubdrose.io

Grok 4.7 Benchmarks


Measured on xai

7 runs
Avg Tokens / Second
12.00
Decode Tokens / Second
Avg Time to First Token (ms)
4200.00
Runs Analysed
7
Last Updated
Sep 24, 2026, 12:49 AM

Throughput distribution

Throughput over time

Grok 4.7xai19tok/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 27 tok/s (99th percentile) · dashed rule is the model's own mean

Every lane measuring this model

2 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
xaivia OpenRouter12.008.7815.404200.007
xaidirect8.684.3313.008420.002

Frequently Asked Questions

How fast is Grok 4.7?
The latest rolling average throughput is 12.00 tokens per second with an average time to first token of 4200.00 ms across 7 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 24, 2026, 12:49 AM.

Related models