llm-benchmarks
githubdrose.io

Perceptron Mk1.5 Benchmarks


Measured on perceptron

11 runs
Avg Tokens / Second
49.70
Decode Tokens / Second
—
Avg Time to First Token (ms)
1000.00
Runs Analysed
11
Last Updated
Oct 26, 2026, 02:25 AM

Throughput distribution

Throughput over time

Perceptron Mk1.5perceptron50tok/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 70 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
perceptronvia OpenRouter49.7029.5066.901000.0011

Frequently Asked Questions

How fast is Perceptron Mk1.5?
The latest rolling average throughput is 49.70 tokens per second with an average time to first token of 1000.00 ms across 11 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 26, 2026, 02:25 AM.

Related models