Benchmark Overview
8.59
4830.00
230
Mar 8, 2026, 03:02 PM
Key Insights
GPT-5.2-pro streams at 8.59 tokens/second on average across the last 230 benchmark runs.
Performance fluctuated by 9.33 tokens/second (108.6% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 4830.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Mar 8, 2026, 03:02 PM based on 230 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 | 8.59 | 4.27 | 13.60 | 4830.00 |
Frequently Asked Questions
The latest rolling average throughput is 8.59 tokens per second with an average time to first token of 4830.00 ms across 230 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 8, 2026, 03:02 PM.