Benchmark Overview
49.40
1.05
797
Oct 25, 2025, 03:53 PM
Key Insights
gpt-3.5-turbo streams at 49.40 tokens/second on average across the last 797 benchmark runs.
Performance fluctuated by 102.50 tokens/second (207.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1.05 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Oct 25, 2025, 03:53 PM based on 797 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 | 49.40 | 10.50 | 113.00 | 1.05 |
Frequently Asked Questions
The latest rolling average throughput is 49.40 tokens per second with an average time to first token of 1.05 ms across 797 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 25, 2025, 03:53 PM.