Benchmark Overview
38.50
0.63
966
Dec 23, 2025, 04:24 PM
Key Insights
gpt-4o streams at 38.50 tokens/second on average across the last 966 benchmark runs.
Performance fluctuated by 85.81 tokens/second (222.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.63 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Dec 23, 2025, 04:24 PM based on 966 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 | 38.50 | 3.69 | 89.50 | 0.63 |
Frequently Asked Questions
The latest rolling average throughput is 38.50 tokens per second with an average time to first token of 0.63 ms across 966 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Dec 23, 2025, 04:24 PM.