Benchmark Overview
23.50
1370.00
2122
Jul 10, 2026, 02:57 AM
Key Insights
gpt-4 streams at 23.50 tokens/second on average across the last 2122 benchmark runs.
Performance fluctuated by 34.90 tokens/second (148.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1370.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jul 10, 2026, 02:57 AM based on 2141 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 | 23.50 | 3.40 | 38.30 | 1370.00 |
Frequently Asked Questions
The latest rolling average throughput is 23.50 tokens per second with an average time to first token of 1370.00 ms across 2122 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 10, 2026, 02:57 AM.