Test Set
In this evaluation, 90% of the test items were either newly created or
extensively adapted, and the remaining 10% were drawn from real examination
papers from the 2024 and 2025 China National College Entrance Examination
(Gaokao), as well as internationally recognized benchmark datasets.
Representative sample questions are provided in Table 1.
| Category | Question |
|---|---|
| Basic Logical Inference (Deductive) | A seminar has 18 participants. The following information
is known: (1) At least 5 young teachers are female. (2) At least 6 female teachers are middle-aged or older. (3) At least 7 young females are teachers. Question: Based on the above information, which of the following conclusions must be true? Options: A) Some young teachers are not female. B) Some young females are not teachers. C) There are at least 11 young teachers. D) There are at least 13 female teachers. |
| Contextual Reasoning(Common-Sense) | What do you call your mother's sister's husband's son's biological elder brother's mother? |
| Contextual Reasoning(Discipline-Based) | Given that b is the arithmetic mean of a and c, and the line ax + by + c = 0 intersects the circle x² + y² + 4y – 1 = 0 at points A and B, what is the minimum value of ∣AB∣? |
| Contextual Reasoning(Decision-Making Under Uncertainty) | A novel infectious disease has broken out, and current vaccine production can only cover 30% of the population. However, the mutation rate of the virus is unpredictable, and the vaccine’s efficacy and side effects are still unclear. What vaccine distribution strategy should be adopted to best control the outbreak, protect vulnerable populations, and address the uncertainties around mutation and vaccine effectiveness? |
| Contextual Reasoning(Moral and Ethical) | As a newcomer to the workplace, you face a manager who is extremely demanding and frequently pressures you. He asks you to participate in ethically questionable practices, such as concealing financial issues within the company, and he claims that doing so is necessary for you to gain his approval and secure promotion opportunities. Would you follow his instructions or adhere to ethical principles? |
Table 1. Representative Sample Questions