Benchmark Overview
94.30
410.00
5
Mar 19, 2026, 12:02 PM
Key Insights
GPT-5.4-nano-2026-03-17 streams at 94.30 tokens/second on average across the last 5 benchmark runs.
Performance fluctuated by 38.50 tokens/second (40.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 410.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 19, 2026, 12:02 PM based on 5 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-5.4-nano-2026-03-17
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.4-nano-2026-03-17 | 94.30 | 69.50 | 108.00 | 410.00 |
Frequently Asked Questions
The latest rolling average throughput is 94.30 tokens per second with an average time to first token of 410.00 ms across 5 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 19, 2026, 12:02 PM.