Benchmark Overview
35.40
4250.00
313
Jun 24, 2026, 09:56 PM
Key Insights
GPT-5 streams at 35.40 tokens/second on average across the last 313 benchmark runs.
Performance fluctuated by 67.51 tokens/second (190.7% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 4250.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 24, 2026, 09:56 PM based on 313 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
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5 | 35.40 | 7.09 | 74.60 | 4250.00 |
Frequently Asked Questions
The latest rolling average throughput is 35.40 tokens per second with an average time to first token of 4250.00 ms across 313 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 24, 2026, 09:56 PM.