Benchmark Overview
38.60
940.00
729
Jul 21, 2026, 03:15 AM
Key Insights
gpt-4o streams at 38.60 tokens/second on average across the last 729 benchmark runs.
Performance fluctuated by 58.27 tokens/second (151.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 940.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jul 21, 2026, 03:15 AM based on 729 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-4o
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | gpt-4o | 38.60 | 5.63 | 63.90 | 940.00 |
Frequently Asked Questions
The latest rolling average throughput is 38.60 tokens per second with an average time to first token of 940.00 ms across 729 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 21, 2026, 03:15 AM.