Benchmark Overview
4.28
320.00
221
May 7, 2026, 08:17 PM
Key Insights
GPT-5-pro streams at 4.28 tokens/second on average across the last 221 benchmark runs.
Performance fluctuated by 6.35 tokens/second (148.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 320.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 7, 2026, 08:17 PM based on 221 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-pro
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5-pro | 4.28 | 1.64 | 7.99 | 320.00 |
Frequently Asked Questions
The latest rolling average throughput is 4.28 tokens per second with an average time to first token of 320.00 ms across 221 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 7, 2026, 08:17 PM.