llm-benchmarks
githubdrose.io

GPT-5 Mini Benchmarks


Measured on openai

379 runs
openai site
Avg Tokens / Second
49.80
Avg Time to First Token (ms)
2430.00
Runs Analysed
379
Last Updated
Aug 16, 2026, 06:44 AM

Throughput distribution

Throughput over time

GPT-5 Miniopenai30tok/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 130 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)
openaiGPT-5 Mini49.804.46122.002430.00

Frequently Asked Questions

How fast is GPT-5 Mini?
The latest rolling average throughput is 49.80 tokens per second with an average time to first token of 2430.00 ms across 379 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 16, 2026, 06:44 AM.

Related models