CUQ
Validated
Chatbot Usability Questionnaire
Sixteen items covering personality, onboarding, understanding, responses, error handling and ease of use for chatbots.
Score many respondents at once
Use one row per respondent and one column per item (Q1…Q16), with raw responses from 1 to 5. An optional first column called id labels each row. Comma, semicolon and tab separated files all work.
Or paste data
When to use it
Evaluating chatbots, virtual assistants and LLM-based conversational products.
How it is scored
- CUQ score = ((Σ odd items − 8) + (40 − Σ even items)) / 64 × 100.
- Like SUS, it ranges from 0 to 100. Published grade norms do not exist yet, so compare against your own baselines or competitor bots.
Reverse-scored items
2, 4, 6, 8, 10, 12, 14, 16. Participants are not told which items are reversed.