Benchmark Overview
59.40
1440.00
160
Jun 17, 2026, 07:43 PM
Key Insights
GPT-5-codex streams at 59.40 tokens/second on average across the last 160 benchmark runs.
Performance fluctuated by 77.48 tokens/second (130.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1440.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 17, 2026, 07:43 PM based on 160 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-codex
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5-codex | 59.40 | 7.42 | 84.90 | 1440.00 |
Frequently Asked Questions
The latest rolling average throughput is 59.40 tokens per second with an average time to first token of 1440.00 ms across 160 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 17, 2026, 07:43 PM.