Benchmark Overview
59.10
1130.00
200
May 20, 2026, 11:17 AM
Key Insights
GPT-5.1-codex streams at 59.10 tokens/second on average across the last 200 benchmark runs.
Performance fluctuated by 45.00 tokens/second (76.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1130.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 11:17 AM based on 200 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
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.1-codex | 59.10 | 27.70 | 72.70 | 1130.00 |
Frequently Asked Questions
The latest rolling average throughput is 59.10 tokens per second with an average time to first token of 1130.00 ms across 200 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 11:17 AM.