AWS Certified AI Practitioner (AIF-C01) — Question 17

Which metric measures the runtime efficiency of operating AI models?

Answer options

• A. Customer satisfaction score (CSAT)
• B. Training time for each epoch
• C. Average response time
• D. Number of training instances

Correct answer: C

Explanation

The average response time is a direct measure of how quickly an AI model can provide outputs after receiving inputs, making it a key indicator of runtime efficiency. In contrast, customer satisfaction score (CSAT) assesses user experience, training time for each epoch relates to model training, and the number of training instances pertains to data volume rather than execution efficiency.