Benchmark Overview
37.00
1140.00
948
Jul 19, 2026, 03:36 PM
Key Insights
gpt-4.1-mini streams at 37.00 tokens/second on average across the last 948 benchmark runs.
Performance fluctuated by 58.59 tokens/second (158.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1140.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jul 19, 2026, 03:36 PM based on 948 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-4.1-mini
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | gpt-4.1-mini | 37.00 | 2.21 | 60.80 | 1140.00 |
Frequently Asked Questions
The latest rolling average throughput is 37.00 tokens per second with an average time to first token of 1140.00 ms across 948 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 19, 2026, 03:36 PM.