llm-benchmarks
githubdrose.io

Kimi K2.7 Code Benchmarks


Measured on cloudflare

29 runs
Avg Tokens / Second
15.70
Decode Tokens / Second
—
Avg Time to First Token (ms)
4300.00
Runs Analysed
29
Last Updated
Oct 12, 2026, 02:34 PM

Throughput distribution

Throughput over time

Kimi K2.7 Codecloudflare71tok/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 124 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
cloudflarevia OpenRouter15.704.6729.604300.0029

Frequently Asked Questions

How fast is Kimi K2.7 Code?
The latest rolling average throughput is 15.70 tokens per second with an average time to first token of 4300.00 ms across 29 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 12, 2026, 02:34 PM.

Related models