Benchmark Overview
85.00
1000.00
399
Jun 28, 2026, 03:26 AM
Key Insights
GPT-5.1-codex-mini streams at 85.00 tokens/second on average across the last 399 benchmark runs.
Performance fluctuated by 96.90 tokens/second (114.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1000.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 28, 2026, 03:26 AM based on 399 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-mini
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.1-codex-mini | 85.00 | 11.10 | 108.00 | 1000.00 |
Frequently Asked Questions
The latest rolling average throughput is 85.00 tokens per second with an average time to first token of 1000.00 ms across 399 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 28, 2026, 03:26 AM.