Benchmark Overview
88.20
1160.00
236
Mar 29, 2026, 09:03 PM
Key Insights
GPT-5.1-codex-max streams at 88.20 tokens/second on average across the last 236 benchmark runs.
Performance fluctuated by 103.00 tokens/second (116.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1160.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Mar 29, 2026, 09:03 PM based on 236 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 | 88.20 | 14.00 | 117.00 | 1160.00 |
Frequently Asked Questions
The latest rolling average throughput is 88.20 tokens per second with an average time to first token of 1160.00 ms across 236 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 29, 2026, 09:03 PM.