Benchmark Overview
16.30
2310.00
792
Jul 21, 2026, 03:41 AM
Key Insights
GPT-5.3-codex streams at 16.30 tokens/second on average across the last 792 benchmark runs.
Performance fluctuated by 32.99 tokens/second (202.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 2310.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jul 21, 2026, 03:41 AM based on 792 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-5.3-codex
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.3-codex | 16.30 | 3.71 | 36.70 | 2310.00 |
Frequently Asked Questions
The latest rolling average throughput is 16.30 tokens per second with an average time to first token of 2310.00 ms across 792 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 21, 2026, 03:41 AM.