Benchmark Overview
35.70
1550.00
159
Jun 12, 2026, 06:17 PM
Key Insights
GPT-5.1 streams at 35.70 tokens/second on average across the last 159 benchmark runs.
Performance fluctuated by 50.85 tokens/second (142.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1550.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 12, 2026, 06:17 PM based on 159 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
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.1 | 35.70 | 7.85 | 58.70 | 1550.00 |
Frequently Asked Questions
The latest rolling average throughput is 35.70 tokens per second with an average time to first token of 1550.00 ms across 159 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 12, 2026, 06:17 PM.