Benchmark Overview
Avg Tokens / Second
15.30
Avg Time to First Token (ms)
1920.00
Runs Analysed
1
Last Updated
Feb 4, 2026, 06:01 PM
Key Insights
gpt-5.2-codex streams at 15.30 tokens/second on average across the last 1 benchmark runs.
Performance fluctuated by 0.00 tokens/second (0.0% coefficient of variation), indicating consistent behavior across benchmark runs.
Average time to first token is 1920.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Feb 4, 2026, 06:01 PM based on 1 total samples.
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | 15.30 | 15.30 | 15.30 | 1920.00 |
Frequently Asked Questions
The latest rolling average throughput is 15.30 tokens per second with an average time to first token of 1920.00 ms across 1 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 4, 2026, 06:01 PM.