Benchmark Overview
88.60
1750.00
314
Jun 24, 2026, 11:31 PM
Key Insights
GPT-5 Nano streams at 88.60 tokens/second on average across the last 314 benchmark runs.
Performance fluctuated by 148.80 tokens/second (167.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1750.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 24, 2026, 11:31 PM based on 314 total samples.
Performance Distribution
Distribution of throughput measurements showing performance consistency across benchmark runs.
Performance Over Time
Historical performance trends showing how throughput has changed over the benchmarking period.
GPT-5 Nano
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5 Nano | 88.60 | 16.20 | 165.00 | 1750.00 |
Frequently Asked Questions
The latest rolling average throughput is 88.60 tokens per second with an average time to first token of 1750.00 ms across 314 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 24, 2026, 11:31 PM.