Benchmark Overview
42.10
1190.00
2177
Jul 21, 2026, 03:24 AM
Key Insights
gpt-3.5-turbo streams at 42.10 tokens/second on average across the last 2177 benchmark runs.
Performance fluctuated by 72.15 tokens/second (171.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1190.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jul 21, 2026, 03:24 AM based on 2185 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 | 3.85 | 76.00 | 1190.00 |
Frequently Asked Questions
The latest rolling average throughput is 42.10 tokens per second with an average time to first token of 1190.00 ms across 2177 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 21, 2026, 03:24 AM.