llm-benchmarks
githubdrose.io

o4 Mini Benchmarks


Measured on openai

677 runs
openai site
Avg Tokens / Second
47.90
Avg Time to First Token (ms)
1680.00
Runs Analysed
677
Last Updated
Aug 9, 2026, 04:59 AM

Throughput distribution

  • o4 Mini openai48 tok/s
0255075100125150

Visible-token throughput, same basis as the table · curves normalised per model

Throughput over time

o4 Miniopenai53tok/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 · shared vertical scale, 0 to 165 tok/s (99th percentile) · dashed rule is the model's own mean · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
openaio4 Mini47.909.02170.001680.00

Frequently Asked Questions

How fast is o4 Mini?
The latest rolling average throughput is 47.90 tokens per second with an average time to first token of 1680.00 ms across 677 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 9, 2026, 04:59 AM.

Related models