API Status

GPT-5-codex Benchmarks

Provider: openai

Explore real-world latency and throughput results for GPT-5-codex. These measurements come from automated benchmarking runs against the provider APIs using the same harness that powers the public cloud dashboard.

Want a broader view of this vendor? Visit the openai provider hub to compare every tracked model side-by-side.

Visit openai Official Website

Benchmark Overview

Avg Tokens / Second

6.92

Avg Time to First Token (ms)

1550.00

Runs Analysed

2

Last Updated

Mar 19, 2026, 12:01 PM

Key Insights

  • GPT-5-codex streams at 6.92 tokens/second on average across the last 2 benchmark runs.

  • Performance fluctuated by 9.95 tokens/second (143.8% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 1550.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.

  • Latest measurements completed on Mar 19, 2026, 12:01 PM based on 2 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

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
openaiGPT-5-codex6.921.9511.901550.00

Frequently Asked Questions

The latest rolling average throughput is 6.92 tokens per second with an average time to first token of 1550.00 ms across 2 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 19, 2026, 12:01 PM.

Related Links