Benchmark Overview
Avg Tokens / Second
17.10
Avg Time to First Token (ms)
1430.00
Runs Analysed
171
Last Updated
Apr 3, 2026, 12:05 PM
Key Insights
gpt-5.2-codex streams at 17.10 tokens/second on average across the last 171 benchmark runs.
Performance fluctuated by 34.43 tokens/second (201.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1430.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Apr 3, 2026, 12:05 PM based on 171 total samples.
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | 17.10 | 1.97 | 36.40 | 1430.00 |
Frequently Asked Questions
The latest rolling average throughput is 17.10 tokens per second with an average time to first token of 1430.00 ms across 171 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 3, 2026, 12:05 PM.