Benchmark Overview
41.70
740.00
312
Jun 24, 2026, 07:46 PM
Key Insights
gpt-4.1 streams at 41.70 tokens/second on average across the last 312 benchmark runs.
Performance fluctuated by 52.20 tokens/second (125.2% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 740.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jun 24, 2026, 07:46 PM based on 312 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
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | gpt-4.1 | 41.70 | 14.70 | 66.90 | 740.00 |
Frequently Asked Questions
The latest rolling average throughput is 41.70 tokens per second with an average time to first token of 740.00 ms across 312 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 24, 2026, 07:46 PM.