Benchmark Overview
60.50
1110.00
571
Jul 21, 2026, 03:12 AM
Key Insights
GPT-5-chat-latest streams at 60.50 tokens/second on average across the last 571 benchmark runs.
Performance fluctuated by 64.70 tokens/second (106.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1110.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jul 21, 2026, 03:12 AM based on 571 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 | 60.50 | 12.90 | 77.60 | 1110.00 |
Frequently Asked Questions
The latest rolling average throughput is 60.50 tokens per second with an average time to first token of 1110.00 ms across 571 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 21, 2026, 03:12 AM.