Benchmark Overview
49.70
1640.00
138
Feb 12, 2026, 06:11 PM
Key Insights
GPT-5.1-codex-max streams at 49.70 tokens/second on average across the last 138 benchmark runs.
Performance fluctuated by 103.54 tokens/second (208.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1640.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Feb 12, 2026, 06:11 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-5.1-codex-max
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5.1-codex-max | 49.70 | 1.46 | 105.00 | 1640.00 |
Frequently Asked Questions
The latest rolling average throughput is 49.70 tokens per second with an average time to first token of 1640.00 ms across 138 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 12, 2026, 06:11 PM.