Benchmark Overview
16.80
680.00
224
May 11, 2026, 02:00 AM
Key Insights
gpt-4 streams at 16.80 tokens/second on average across the last 224 benchmark runs.
Performance fluctuated by 17.98 tokens/second (107.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 680.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 11, 2026, 02:00 AM based on 224 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 | 16.80 | 7.82 | 25.80 | 680.00 |
Frequently Asked Questions
The latest rolling average throughput is 16.80 tokens per second with an average time to first token of 680.00 ms across 224 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 11, 2026, 02:00 AM.