Choose an LLM by use case

What do you want to do?

Pick a use case to see which models to choose.

Price ($ / 1M tokens)

Ask questions
Top-ratedHighest rated
Gemini 4 Argon $4
On a budgetOn a budget
Gemini 3.8 Flash $1.5
Write text
Top-ratedHighest rated
Claude Opus 5.5 $8
On a budgetOn a budget
Gemini 3.7 Flash $1.5
Summarize long documents
Top-ratedHighest rated
o3 ChatGPT input $2
On a budgetOn a budget
same
Chat or translate in Japanese
Top-ratedHighest rated
△Claude Fable 5.1 $20
On a budgetOn a budget
Gemini 3.7 Flash $1.5
Write code
Top-ratedHighest rated
△Gemini 4 Argon $4
On a budgetOn a budget
Muse Spark 1.2 Meta AI $2
Solve math problems
Top-ratedHighest rated
△Gemini 4 Argon $4
On a budgetOn a budget
GLM-5.3 Flash Z.ai Open weights $0.24

Below are the answers for each use case.

Think

Make

Read

Talk

By field of work

△ marks a model whose rating is within the margin of error of a cheaper model (about the same).
Prices are a guide to what developers pay per million tokens through the API, separate from app subscriptions (details under "How to read this page" on each use-case page).

Rankings by benchmark (in detail)

Robot Workshop

Buy robots in the shop, line them up, and let them battle another team on their own until you reach 10 wins.

Data: Arena, Epoch AI, Swallow LLM team (CC BY 4.0), Models.dev (MIT), updated 2026-⁠10-⁠24, data sources