Benchmark Overview
35.30
1120.00
160
Jun 11, 2026, 03:15 PM
Key Insights
gpt-4o streams at 35.30 tokens/second on average across the last 160 benchmark runs.
Performance fluctuated by 53.63 tokens/second (151.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1120.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 11, 2026, 03:15 PM based on 160 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 | 35.30 | 7.07 | 60.70 | 1120.00 |
Frequently Asked Questions
The latest rolling average throughput is 35.30 tokens per second with an average time to first token of 1120.00 ms across 160 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 11, 2026, 03:15 PM.