llm-benchmarks
githubdrose.io

GPT-5.1-codex-max Benchmarks


Measured on openai

248 runs
openai site
Avg Tokens / Second
60.90
Avg Time to First Token (ms)
2900.00
Runs Analysed
248
Last Updated
Jul 21, 2026, 03:12 AM

Throughput distribution

  • GPT-5.1-codex-max openai61 tok/s
0255075100125

Visible-token throughput, same basis as the table · curves normalised per model

Throughput over time

GPT-5.1-codex-maxopenai29tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 129 tok/s (99th percentile) · dashed rule is the model's own mean

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
openaiGPT-5.1-codex-max60.906.97122.002900.00

Frequently Asked Questions

How fast is GPT-5.1-codex-max?
The latest rolling average throughput is 60.90 tokens per second with an average time to first token of 2900.00 ms across 248 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 21, 2026, 03:12 AM.

Related models