Benchmark Overview
57.80
1860.00
196
May 20, 2026, 06:50 AM
Key Insights
GPT-5.1-codex-max streams at 57.80 tokens/second on average across the last 196 benchmark runs.
Performance fluctuated by 98.90 tokens/second (171.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1860.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 06:50 AM based on 196 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 | 57.80 | 11.10 | 110.00 | 1860.00 |
Frequently Asked Questions
The latest rolling average throughput is 57.80 tokens per second with an average time to first token of 1860.00 ms across 196 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 06:50 AM.