Benchmark Overview
100.00
350.00
5
Mar 19, 2026, 12:02 PM
Key Insights
GPT-5.4-mini-2026-03-17 streams at 100.00 tokens/second on average across the last 5 benchmark runs.
Performance fluctuated by 40.00 tokens/second (40.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 350.00 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-mini-2026-03-17
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.4-mini-2026-03-17 | 100.00 | 79.00 | 119.00 | 350.00 |
Frequently Asked Questions
The latest rolling average throughput is 100.00 tokens per second with an average time to first token of 350.00 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.