Benchmark Overview
38.90
1960.00
159
Jun 17, 2026, 03:39 PM
Key Insights
GPT-5.2-chat-latest streams at 38.90 tokens/second on average across the last 159 benchmark runs.
Performance fluctuated by 40.77 tokens/second (104.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1960.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 17, 2026, 03:39 PM based on 159 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-chat-latest
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.2-chat-latest | 38.90 | 9.43 | 50.20 | 1960.00 |
Frequently Asked Questions
The latest rolling average throughput is 38.90 tokens per second with an average time to first token of 1960.00 ms across 159 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 17, 2026, 03:39 PM.