Benchmark Overview
42.30
1310.00
198
May 20, 2026, 11:12 AM
Key Insights
GPT-5.1-chat-latest streams at 42.30 tokens/second on average across the last 198 benchmark runs.
Performance fluctuated by 42.10 tokens/second (99.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1310.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 11:12 AM based on 198 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-5.1-chat-latest
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.1-chat-latest | 42.30 | 18.40 | 60.50 | 1310.00 |
Frequently Asked Questions
The latest rolling average throughput is 42.30 tokens per second with an average time to first token of 1310.00 ms across 198 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 11:12 AM.