Benchmark Overview
49.00
1220.00
6
Aug 4, 2026, 01:50 PM
Key Insights
GPT-5.4-nano streams at 49.00 tokens/second on average across the last 6 benchmark runs.
Performance fluctuated by 29.40 tokens/second (60.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1220.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Aug 4, 2026, 01:50 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-nano
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.4-nano | 49.00 | 34.50 | 63.90 | 1220.00 |
Frequently Asked Questions
The latest rolling average throughput is 49.00 tokens per second with an average time to first token of 1220.00 ms across 6 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 4, 2026, 01:50 PM.