Benchmark Overview
8.85
31500.00
21
May 10, 2026, 09:25 PM
Key Insights
GPT-5.5-pro streams at 8.85 tokens/second on average across the last 21 benchmark runs.
Performance fluctuated by 13.67 tokens/second (154.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 31500.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 10, 2026, 09:25 PM based on 21 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-pro
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.5-pro | 8.85 | 3.53 | 17.20 | 31500.00 |
Frequently Asked Questions
The latest rolling average throughput is 8.85 tokens per second with an average time to first token of 31500.00 ms across 21 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 10, 2026, 09:25 PM.