Benchmark Overview
Avg Tokens / Second
21.80
Avg Time to First Token (ms)
1340.00
Runs Analysed
162
Last Updated
Apr 12, 2026, 09:02 AM
Key Insights
gpt-5.2-codex streams at 21.80 tokens/second on average across the last 162 benchmark runs.
Performance fluctuated by 58.97 tokens/second (270.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1340.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Apr 12, 2026, 09:02 AM based on 162 total samples.
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | 21.80 | 2.83 | 61.80 | 1340.00 |
Frequently Asked Questions
The latest rolling average throughput is 21.80 tokens per second with an average time to first token of 1340.00 ms across 162 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 12, 2026, 09:02 AM.