Benchmark Overview
86.70
450.00
124
Apr 3, 2026, 09:02 AM
Key Insights
GPT-5.4-nano-2026-03-17 streams at 86.70 tokens/second on average across the last 124 benchmark runs.
Performance fluctuated by 88.20 tokens/second (101.7% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 450.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Apr 3, 2026, 09:02 AM based on 124 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 | 86.70 | 36.80 | 125.00 | 450.00 |
Frequently Asked Questions
The latest rolling average throughput is 86.70 tokens per second with an average time to first token of 450.00 ms across 124 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 3, 2026, 09:02 AM.