Skip to content

Evaluation

GPT-4 qualitative evaluation / expert red teaming

Stress testing, boundary testing, and red teaming by external experts (from August 2022)

Red teaming & adversarial testing OpenAI

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

gpt-4
OpenAI

rich detail 11 method fields published

See how this test was run