Benchmark Overview
64.00
2750.00
395
Jun 27, 2026, 11:43 PM
Key Insights
GPT-5.1-codex-max streams at 64.00 tokens/second on average across the last 395 benchmark runs.
Performance fluctuated by 102.54 tokens/second (160.2% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 2750.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 27, 2026, 11:43 PM based on 395 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-5.1-codex-max
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.1-codex-max | 64.00 | 9.46 | 112.00 | 2750.00 |
Frequently Asked Questions
The latest rolling average throughput is 64.00 tokens per second with an average time to first token of 2750.00 ms across 395 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 27, 2026, 11:43 PM.