OpenAI Factuality (Internal)

OpenAI's internal test uses prompts designed to provoke factual mistakes. The score is the percentage of answers containing at least one factual error, at the model's best published reasoning effort. It is not the percentage of individual claims that are wrong or an error rate for everyday use. Lower is better.

GPT-6.1 Terra by OpenAI holds the best OpenAI Factuality (Internal) result among tracked models, at 4.3% (released Oct 26 2026). Lower scores are better on this benchmark.

1. GPT-6.1 Terra (OpenAI) — 4.3%.

1 tracked model has a published OpenAI Factuality (Internal) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.