GPT-5 Nano by openai Benchmarks

No Successful Benchmarks

This model has never returned successful benchmark results. It may be misconfigured or unavailable.

Last benchmark: May 19, 2026

Benchmark Overview

Avg Tokens / Second

81.70

Avg Time to First Token (ms)

760.00

Runs Analysed

198

Last Updated

May 19, 2026, 10:53 PM

GPT-5 Nano streams at 81.70 tokens/second on average across the last 198 benchmark runs.
Performance fluctuated by 131.30 tokens/second (160.7% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 760.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 19, 2026, 10:53 PM based on 198 total samples.

Distribution of throughput measurements showing performance consistency across benchmark runs.

Historical performance trends showing how throughput has changed over the benchmarking period.

Provider	Model	Avg Toks/Sec	Min	Max	Avg TTF (ms)
openai	GPT-5 Nano	81.70	26.70	158.00	760.00

The latest rolling average throughput is 81.70 tokens per second with an average time to first token of 760.00 ms across 198 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 19, 2026, 10:53 PM.