Benchmark Overview
48.20
980.00
300
Jun 24, 2026, 09:07 AM
Key Insights
gpt-4.1-nano streams at 48.20 tokens/second on average across the last 300 benchmark runs.
Performance fluctuated by 80.24 tokens/second (166.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 980.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jun 24, 2026, 09:07 AM based on 300 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-nano
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | gpt-4.1-nano | 48.20 | 2.56 | 82.80 | 980.00 |
Frequently Asked Questions
The latest rolling average throughput is 48.20 tokens per second with an average time to first token of 980.00 ms across 300 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 24, 2026, 09:07 AM.