llm-benchmarks
githubdrose.io

Hy4 flash Benchmarks


Measured on tencent

23 runs
Avg Tokens / Second
30.00
Decode Tokens / Second
—
Avg Time to First Token (ms)
1900.00
Runs Analysed
23
Last Updated
Nov 22, 2026, 03:13 PM

Throughput distribution

Throughput over time

Hy4 flashtencent30tok/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 50 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
tencentvia OpenRouter30.0014.5047.201900.0023
tencentdirect33.0033.0033.001450.001

Frequently Asked Questions

How fast is Hy4 flash?
The latest rolling average throughput is 30.00 tokens per second with an average time to first token of 1900.00 ms across 23 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 22, 2026, 03:13 PM.

Related models