Enkrypt AI Rating represents model safety level measured by analyzing model vulnerabilities. It is calculated by inversely mapping the NIST Risk Score (ranging from 0 to 62.5) onto a rating scale from 5 (safe) to 0 (risky).

Model’s MMLU Score indicating its performance. (Source: Internet)

A Ratio of model performance to its NIST Risk score. A higher ratio indicates a better model.

The NIST Risk Score denotes how vulnerable an AI model is to NIST Risks like Bias, Harmful content, Toxicity, CBRN, and Insecure Code Generation. Risk in each of the tests is denoted by percentage of successful attacks. NIST Risk Score is calculated by taking an average of risk found for each test.