Benchmark Overview
68.40
350.00
240
Apr 3, 2026, 12:05 PM
Key Insights
gpt-3.5-turbo streams at 68.40 tokens/second on average across the last 240 benchmark runs.
Performance fluctuated by 83.70 tokens/second (122.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 350.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Apr 3, 2026, 12:05 PM based on 240 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 | 68.40 | 36.30 | 120.00 | 350.00 |
Frequently Asked Questions
The latest rolling average throughput is 68.40 tokens per second with an average time to first token of 350.00 ms across 240 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 3, 2026, 12:05 PM.