Benchmark Overview
50.30
460.00
210
Apr 14, 2026, 12:03 AM
Key Insights
gpt-4o streams at 50.30 tokens/second on average across the last 210 benchmark runs.
Performance fluctuated by 101.57 tokens/second (201.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 460.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Apr 14, 2026, 12:03 AM based on 210 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 | 50.30 | 5.43 | 107.00 | 460.00 |
Frequently Asked Questions
The latest rolling average throughput is 50.30 tokens per second with an average time to first token of 460.00 ms across 210 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 14, 2026, 12:03 AM.