Benchmark Overview
15.00
29200.00
396
Jun 28, 2026, 01:53 AM
Key Insights
GPT-5.2-pro streams at 15.00 tokens/second on average across the last 396 benchmark runs.
Performance fluctuated by 17.90 tokens/second (119.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 29200.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 28, 2026, 01:53 AM based on 396 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-5.2-pro
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.2-pro | 15.00 | 4.60 | 22.50 | 29200.00 |
Frequently Asked Questions
The latest rolling average throughput is 15.00 tokens per second with an average time to first token of 29200.00 ms across 396 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 28, 2026, 01:53 AM.