Benchmark Overview
18.00
1000.00
574
May 20, 2026, 11:23 AM
Key Insights
gpt-4 streams at 18.00 tokens/second on average across the last 574 benchmark runs.
Performance fluctuated by 25.38 tokens/second (141.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1000.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 11:23 AM based on 597 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-4
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | gpt-4 | 18.00 | 4.72 | 30.10 | 1000.00 |
Frequently Asked Questions
The latest rolling average throughput is 18.00 tokens per second with an average time to first token of 1000.00 ms across 574 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 11:23 AM.