Benchmark Overview
10.70
1530.00
110
Apr 3, 2026, 09:01 AM
Key Insights
GPT-5.2-chat-latest streams at 10.70 tokens/second on average across the last 110 benchmark runs.
Performance fluctuated by 25.44 tokens/second (237.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1530.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Apr 3, 2026, 09:01 AM based on 110 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 | 10.70 | 1.06 | 26.50 | 1530.00 |
Frequently Asked Questions
The latest rolling average throughput is 10.70 tokens per second with an average time to first token of 1530.00 ms across 110 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 3, 2026, 09:01 AM.