Benchmark Overview
62.30
520.00
211
May 3, 2026, 09:02 PM
Key Insights
GPT-5.4-mini streams at 62.30 tokens/second on average across the last 211 benchmark runs.
Performance fluctuated by 69.00 tokens/second (110.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 520.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 3, 2026, 09:02 PM based on 211 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
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.4-mini | 62.30 | 22.40 | 91.40 | 520.00 |
Frequently Asked Questions
The latest rolling average throughput is 62.30 tokens per second with an average time to first token of 520.00 ms across 211 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 3, 2026, 09:02 PM.