Benchmark Overview
19.40
2090.00
321
Jun 25, 2026, 04:24 AM
Key Insights
GPT-5.5 streams at 19.40 tokens/second on average across the last 321 benchmark runs.
Performance fluctuated by 22.47 tokens/second (115.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 2090.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 25, 2026, 04:24 AM based on 321 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-5.5
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.5 | 19.40 | 7.53 | 30.00 | 2090.00 |
Frequently Asked Questions
The latest rolling average throughput is 19.40 tokens per second with an average time to first token of 2090.00 ms across 321 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 25, 2026, 04:24 AM.