llm-benchmarks
githubdrose.io

DeepSeek V4 Pro 0813 Benchmarks


Measured on venice

118 runs
Avg Tokens / Second
--
Decode Tokens / Second
—
Avg Time to First Token (ms)
0.00
Runs Analysed
118
Last Updated
Nov 13, 2026, 10:56 PM

Throughput over time

DeepSeek V4 Pro 0813wafer54tok/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 87 tok/s (99th percentile) · dashed rule is the model's own mean · 5 further providers not drawn

Every lane measuring this model

0 measured · live first · a lane is a provider, a catalogue id and a transport

No recent benchmark samples were recorded for this timeframe.

Frequently Asked Questions

How fast is DeepSeek V4 Pro 0813?
The latest rolling average throughput is -- tokens per second with an average time to first token of 0.00 ms across 118 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 13, 2026, 10:56 PM.

Related models