Models have different levels of quality and speed. Here’s a list of our recommendations:

Best Models (in General)

Claude Sonnet 4 - This is currently the best overall model for coding tasks.

Gemini 2.5 Pro - Excellent quality but may have longer response times due to reasoning.

If one isn’t giving you good results, try the other. Sometimes one model is good at a thing that the other model is bad at.

Note: Claude Sonnet 4 is a very eager model, and tries to run lots of actions.

Best Thinking Model

OpenAI o3 - Takes time to think through problems but delivers often perfect results.

o3 does not have access to tools in Alex, in order to keep the output quality high. So make sure to pass all the files it needs into its context first.

All Available Models

Here’s the ranking of all models available in Alex:

  1. Claude Sonnet 4
  2. Gemini 2.5 Pro
  3. Claude 3.5 Sonnet
  4. Gemini 2.5 Flash
  5. OpenAI o3
  6. OpenAI o4 Mini (06.19)
  7. OpenAI GPT 4.1
  8. DeepSeek R1
  9. DeepSeek V3 (03.24)

These are just our rankings, based on our experience with general iOS/Swift development. For general SWE rankings, see Aider’s Leaderboard: https://aider.chat/docs/leaderboards/

Local Models

If you’d like to use local models, here’s our ranking:

  1. Qwen2.5 Coder 32B (Best, but slowest to run)
  2. Qwen2.5 Coder 14B
  3. Gemma3 27b QAT
  4. Gemma3 12b QAT

We generally don’t recommend running local models, due to their poor performance compared to hosted models.