Benchmark Overview
61.40
1080.00
949
Jul 19, 2026, 08:07 PM
Key Insights
GPT-5-chat-latest streams at 61.40 tokens/second on average across the last 949 benchmark runs.
Performance fluctuated by 73.47 tokens/second (119.7% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1080.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jul 19, 2026, 08:07 PM based on 949 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 | 61.40 | 4.63 | 78.10 | 1080.00 |
Frequently Asked Questions
The latest rolling average throughput is 61.40 tokens per second with an average time to first token of 1080.00 ms across 949 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 19, 2026, 08:07 PM.