Benchmark Overview
63.00
340.00
239
Feb 21, 2026, 06:03 AM
Key Insights
gpt-4o streams at 63.00 tokens/second on average across the last 239 benchmark runs.
Performance fluctuated by 99.00 tokens/second (157.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 340.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Feb 21, 2026, 06:03 AM based on 239 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 | 63.00 | 13.00 | 112.00 | 340.00 |
Frequently Asked Questions
The latest rolling average throughput is 63.00 tokens per second with an average time to first token of 340.00 ms across 239 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 21, 2026, 06:03 AM.