Benchmark Overview
42.10
1270.00
1027
Jun 26, 2026, 01:24 AM
Key Insights
gpt-3.5-turbo streams at 42.10 tokens/second on average across the last 1027 benchmark runs.
Performance fluctuated by 74.29 tokens/second (176.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1270.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jun 26, 2026, 01:24 AM based on 1032 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-3.5-turbo
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | gpt-3.5-turbo | 42.10 | 1.41 | 75.70 | 1270.00 |
Frequently Asked Questions
The latest rolling average throughput is 42.10 tokens per second with an average time to first token of 1270.00 ms across 1027 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 26, 2026, 01:24 AM.