Benchmark Overview
35.40
500.00
138
Mar 26, 2026, 03:05 PM
Key Insights
gpt-4-turbo streams at 35.40 tokens/second on average across the last 138 benchmark runs.
Performance fluctuated by 47.80 tokens/second (135.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 500.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 26, 2026, 03:05 PM based on 138 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-4-turbo
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | gpt-4-turbo | 35.40 | 1.00 | 48.80 | 500.00 |
Frequently Asked Questions
The latest rolling average throughput is 35.40 tokens per second with an average time to first token of 500.00 ms across 138 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 26, 2026, 03:05 PM.