Benchmark Overview
91.30
1560.00
90
Mar 11, 2026, 09:05 PM
Key Insights
gpt-4o streams at 91.30 tokens/second on average across the last 90 benchmark runs.
Performance fluctuated by 107.80 tokens/second (118.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1560.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Mar 11, 2026, 09:05 PM based on 90 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 | 91.30 | 22.20 | 130.00 | 1560.00 |
Frequently Asked Questions
The latest rolling average throughput is 91.30 tokens per second with an average time to first token of 1560.00 ms across 90 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 11, 2026, 09:05 PM.