Benchmark Overview
28.10
820.00
192
May 22, 2026, 09:58 PM
Key Insights
gpt-4o-mini streams at 28.10 tokens/second on average across the last 192 benchmark runs.
Performance fluctuated by 32.90 tokens/second (117.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 820.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 22, 2026, 09:58 PM based on 192 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-mini
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | gpt-4o-mini | 28.10 | 10.30 | 43.20 | 820.00 |
Frequently Asked Questions
The latest rolling average throughput is 28.10 tokens per second with an average time to first token of 820.00 ms across 192 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 22, 2026, 09:58 PM.