Benchmark Overview
39.30
790.00
557
May 20, 2026, 02:19 AM
Key Insights
gpt-3.5-turbo streams at 39.30 tokens/second on average across the last 557 benchmark runs.
Performance fluctuated by 64.00 tokens/second (162.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 790.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 02:19 AM based on 600 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 | 39.30 | 15.20 | 79.20 | 790.00 |
Frequently Asked Questions
The latest rolling average throughput is 39.30 tokens per second with an average time to first token of 790.00 ms across 557 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 02:19 AM.