GPT-5.1 Instant and GPT-5.1 Thinking System Card Addendum
OpenAI just released safety metrics for GPT-5.1 Instant and Thinking—including new evaluations for mental health and emotional reliance.
Why it matters
GPT-5.1 is shipping with expanded safety benchmarks that signal OpenAI's focus on deployment risk mitigation for high-stakes use cases. This reveals what the company considers table-stakes for production models in 2025.
The key facts
9 to knowGPT-5.1 Instant and Thinking variants launched
New safety metrics for mental health and emotional reliance
System card addendum published (suggests iterative safety governance)
Indicates OpenAI's expanded safety evaluation scope post-release
GPT-5.1 Instant variant released
GPT-5.1 Thinking variant released
New safety evaluations for mental health added
New safety evaluations for emotional reliance added
System card addendum published Nov 12 2025
Go to the source
OpenAI Blogopenai.com
Publisher excerpt: This GPT-5 system card addendum provides updated safety metrics for GPT-5.1 Instant and Thinking, including new evaluations for mental health and emotional reliance.