Benchmark Overview
14.00
9350.00
207
May 14, 2026, 02:18 AM
Key Insights
GPT-5.2-pro streams at 14.00 tokens/second on average across the last 207 benchmark runs.
Performance fluctuated by 9.00 tokens/second (64.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 9350.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 14, 2026, 02:18 AM based on 207 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 | 14.00 | 9.70 | 18.70 | 9350.00 |
Frequently Asked Questions
The latest rolling average throughput is 14.00 tokens per second with an average time to first token of 9350.00 ms across 207 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 14, 2026, 02:18 AM.