Benchmark Overview
23.80
1650.00
6
Mar 12, 2026, 03:03 PM
Key Insights
GPT-5.4 streams at 23.80 tokens/second on average across the last 6 benchmark runs.
Performance fluctuated by 11.10 tokens/second (46.6% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1650.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Mar 12, 2026, 03:03 PM based on 6 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
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.4 | 23.80 | 19.10 | 30.20 | 1650.00 |
Frequently Asked Questions
The latest rolling average throughput is 23.80 tokens per second with an average time to first token of 1650.00 ms across 6 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 12, 2026, 03:03 PM.