Benchmark Overview
8.13
1940.00
31
Apr 3, 2026, 03:01 AM
Key Insights
GPT-5-codex streams at 8.13 tokens/second on average across the last 31 benchmark runs.
Performance fluctuated by 21.78 tokens/second (267.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1940.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Apr 3, 2026, 03:01 AM based on 31 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-codex
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | GPT-5-codex | 8.13 | 1.12 | 22.90 | 1940.00 |
Frequently Asked Questions
The latest rolling average throughput is 8.13 tokens per second with an average time to first token of 1940.00 ms across 31 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 3, 2026, 03:01 AM.