Benchmark Overview
Avg Tokens / Second
35.60
Avg Time to First Token (ms)
1170.00
Runs Analysed
225
Last Updated
May 6, 2026, 03:02 AM
Key Insights
gpt-5.2-codex streams at 35.60 tokens/second on average across the last 225 benchmark runs.
Performance fluctuated by 61.68 tokens/second (173.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1170.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 6, 2026, 03:02 AM based on 225 total samples.
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | 35.60 | 6.02 | 67.70 | 1170.00 |
Frequently Asked Questions
The latest rolling average throughput is 35.60 tokens per second with an average time to first token of 1170.00 ms across 225 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 6, 2026, 03:02 AM.