llm-benchmarks
githubdrose.io

DeepSeek V4 Flash 0423 Benchmarks


Measured on fireworks

1 runs
fireworks site
Avg Tokens / Second
9.08
Decode Tokens / Second
—
Avg Time to First Token (ms)
6360.00
Runs Analysed
1
Last Updated
Oct 29, 2026, 10:22 PM

Throughput distribution

Throughput over time

No time series data available.

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
fireworksvia OpenRouter9.089.089.086360.001

Frequently Asked Questions

How fast is DeepSeek V4 Flash 0423?
The latest rolling average throughput is 9.08 tokens per second with an average time to first token of 6360.00 ms across 1 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 29, 2026, 10:22 PM.