Benchmark Overview
43.90
1230.00
675
Aug 2, 2026, 01:57 AM
Key Insights
GPT-5.4-mini streams at 43.90 tokens/second on average across the last 675 benchmark runs.
Performance fluctuated by 71.12 tokens/second (162.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1230.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Aug 2, 2026, 01:57 AM based on 675 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 | 43.90 | 5.08 | 76.20 | 1230.00 |
Frequently Asked Questions
The latest rolling average throughput is 43.90 tokens per second with an average time to first token of 1230.00 ms across 675 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 2, 2026, 01:57 AM.