Benchmark Overview
27.60
2140.00
26
Jul 30, 2026, 01:58 PM
Key Insights
GPT-5.6-luna streams at 27.60 tokens/second on average across the last 26 benchmark runs.
Performance fluctuated by 31.25 tokens/second (113.2% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 2140.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jul 30, 2026, 01:58 PM based on 26 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-5.6-luna
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.6-luna | 27.60 | 9.55 | 40.80 | 2140.00 |
Frequently Asked Questions
The latest rolling average throughput is 27.60 tokens per second with an average time to first token of 2140.00 ms across 26 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 30, 2026, 01:58 PM.