Benchmark Overview
48.50
850.00
203
May 19, 2026, 09:35 PM
Key Insights
GPT-5-chat-latest streams at 48.50 tokens/second on average across the last 203 benchmark runs.
Performance fluctuated by 54.10 tokens/second (111.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 850.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 19, 2026, 09:35 PM based on 203 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-chat-latest
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5-chat-latest | 48.50 | 14.50 | 68.60 | 850.00 |
Frequently Asked Questions
The latest rolling average throughput is 48.50 tokens per second with an average time to first token of 850.00 ms across 203 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 19, 2026, 09:35 PM.