Benchmark Overview
12.00
24500.00
945
Jul 19, 2026, 02:38 PM
Key Insights
GPT-5.5-pro streams at 12.00 tokens/second on average across the last 945 benchmark runs.
Performance fluctuated by 34.92 tokens/second (291.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 24500.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jul 19, 2026, 02:38 PM based on 945 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 | 12.00 | 0.48 | 35.40 | 24500.00 |
Frequently Asked Questions
The latest rolling average throughput is 12.00 tokens per second with an average time to first token of 24500.00 ms across 945 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 19, 2026, 02:38 PM.