---
title: "Model selection — CCAR-P 2.1 practice questions"
description: "6 CCAR-P practice questions on objective 2.1: Model selection. Part of domain 2, Models, Prompting & Context Engineering."
url: "https://claudearchitectguide.com/drill/obj/2-1"
image: "https://claudearchitectguide.com/og.png"
---

Objective 2.1 · Domain 2 · 13% of the exam

# Select appropriate Claude models based on trade-offs

Model selection across the Claude family, judged on the trade-off the scenario states and not on capability alone. The reasoning has the same shape every time. The largest model is right only when the task genuinely needs it, and a cheaper, faster model is right far more often than instinct suggests, particularly for classification, extraction and routing steps inside a larger pipeline. If a stem gives you a per-request latency budget or a volume figure, that is the constraint deciding the answer.

6 questions · answers and explanations shown as you go · free, no sign-up

## The rest of domain 2: Models, Prompting & Context Engineering

This domain is 13% of a scored form, about 8 of the 63 questions, spread across 5 objectives. [Drill the whole domain](https://claudearchitectguide.com/drill/2) or pick another objective below.

- [2.2 Design system prompts, templates, and guardrails (5)](https://claudearchitectguide.com/drill/obj/2-2)
- [2.3 Apply prompt engineering techniques (zero-shot, few-shot, chain-of-thought)(5)](https://claudearchitectguide.com/drill/obj/2-3)
- [2.4 Optimize context windows and manage token usage (5)](https://claudearchitectguide.com/drill/obj/2-4)
- [2.5 Implement prompt reuse strategies (caching, modular prompts, Skills)(5)](https://claudearchitectguide.com/drill/obj/2-5)

One objective is a narrow slice. A full-length timed mock is what tells you whether the whole thing holds together.

[Sit a timed mock →](https://claudearchitectguide.com/exam)
