Skip to content

Model Selection & Routing

Weight: 10%
Sources verified Dec 22

Why It Matters

GitHub Copilot now supports Claude (Opus/Sonnet), GPT-4, and Gemini. Cursor and Windsurf offer even more options. Mature users know that different models excel at different tasks, and the 100x cost difference between models matters. IDC predicts 70% of top enterprises will use dynamic model routing by 2028.

2025 Context

Claude Opus 4.5 leads SWE-bench (80.9%), but GPT-5-Codex (74.5%) and Gemini Flash (faster, cheaper) each excel at different tasks. Augment Code's production data shows developers assembling 'model alloys'—matching Sonnet 4.5 to multi-file reasoning, Sonnet 4.0 to fast structured tasks, GPT-5 to explanatory contexts. The skill gap has moved from 'which is best?' to 'best for what?'

Assessment Questions (5)

Maximum possible score: 19 points

Q1 single choice 4 pts

Are you aware that GitHub Copilot supports multiple AI models (Claude, GPT, Gemini)?

[0] No, I didn't know this
[1] Yes, but I always use the default
[2] Yes, I've tried different models occasionally
[4] Yes, I regularly switch based on the task

Q2 single choice 4 pts

How do you select AI models for different coding tasks?

[0] I use whatever is default—I don't think about model selection
[1] I use the same model for everything (my favorite)
[2] I have rough preferences (e.g., Claude for refactoring, GPT for docs)
[3] I systematically match models to tasks, considering cost and speed tradeoffs
[4] I assemble 'model alloys'—matching cognitive styles (reasoning vs fast) to task profiles

Q3 multi select 5 pts

Which of the following model-task pairings do you use?

[1] Claude Opus/Sonnet for complex refactoring or architecture
[1] Gemini Flash or GPT-3.5 for simple tasks (tests, docs)
[1] Reasoning models (o3, Claude thinking) for debugging
[1] Gemini for very long context (1M+ tokens)
[1] Thinking triggers (think hard, ultrathink) for complex problems
[0] I don't think about model selection

Note: Thinking triggers (ultrathink) activate extended reasoning budgets in Claude Code. Gemini Deep Think uses parallel reasoning. Different cognitive styles for different tasks.

Q4 single choice 3 pts

Are you aware of the cost differences between AI models?

[0] No, I don't think about cost
[1] Vaguely—I know some are more expensive
[2] Yes, I know approximate cost ratios
[3] Yes, I factor cost into model selection decisions

Q5 single choice 3 pts

When selecting a model for a task, do you consider speed/latency tradeoffs?

[0] No, I don't think about latency
[1] Sometimes—I notice when a model is slow but don't switch
[2] Yes, I use faster models for simple tasks to avoid waiting
[3] Yes, I balance latency, quality, and cost based on task urgency

Practice Conversations (1)

Learn through simulated conversations that demonstrate key concepts.

Tempered AI Forged Through Practice, Not Hype

Keyboard Shortcuts

j
Next page
k
Previous page
h
Section home
/
Search
?
Show shortcuts
m
Toggle sidebar
Esc
Close modal
Shift+R
Reset all progress
? Keyboard shortcuts