Learning path
AI Models
Pick the right model for the job without drowning in benchmarks.
Compare frontier, open-weight, Chinese, and cost-efficient models with plain-English decision frameworks.
What Is an AI Model Tier List? A Beginner's Guide to Comparing LLMs (2026)
Why 'best model' is the wrong question — and a 4-tier mental model that maps any workload to the cheapest model that will actually handle it.
Haiku vs Sonnet vs Opus: The Anthropic Model Family Explained (2026)
Anthropic ships three Claude tiers in 2026 — Haiku, Sonnet, Opus — and most beginners waste hundreds of dollars a month picking the wrong one. Here's the plain-English framework for matching tier to task.
Chinese Open-Weight Models in 2026: DeepSeek, Kimi, Qwen, GLM, MiniMax, StepFun
Six Chinese open-weight labs, what each is best at, and how to pick the right one without confusing 'open-weight' with 'open-source' or 'free API'.
Qwen, MiniMax, and GLM: The Cost-Efficient AI Model Tier for 2026
Qwen, MiniMax, and GLM handle 80% of daily work at 5–20x lower cost than Claude Opus 4.8. Pick by workload, not by price.
Frontier vs Open-Weight AI Models: How to Pick in 2026 (Decision Framework)
The synthesis of L01–L04 into a single decision framework: given a task, what type of model do you choose — and when do you switch tiers mid-project?