Benchmark Overview
50.80
1580.00
213
May 13, 2026, 09:34 PM
Key Insights
GPT-5.1-codex-max streams at 50.80 tokens/second on average across the last 213 benchmark runs.
Performance fluctuated by 69.70 tokens/second (137.2% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1580.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 13, 2026, 09:34 PM based on 213 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 | 50.80 | 11.10 | 80.80 | 1580.00 |
Frequently Asked Questions
The latest rolling average throughput is 50.80 tokens per second with an average time to first token of 1580.00 ms across 213 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 13, 2026, 09:34 PM.