How To Optimize Your Usage: The Best AI Models to Use, version 2.2

How To
19

gpt-5-high >= gpt-5 > Grok Code Fast

  • gpt-5-high: Stable and smart
  • gpt-5: Sometimes I use it to save money, but I’m not sure if I’m really saving.
  • Grok Code Fast: Excellent for gathering information and simple tasks.
  • UPD4: gpt-5-mini slightly smarter and secure than GFC, so you can use it for simple tasks or reasoning (ChatGPT Free Plan uses gpt-5-mini)
  • Gemini 2.5 Pro outdated relative to gpt-5 and Grok 4
  • Grok 4 probably still broken. I’ve already lost hope and I don’t want to check.
  • Claude 4.5 Sonnet Thinking / Claude 4.5 Sonnet is too expensive;
    UPD2: The best model for creating and work with huge documentation.
    UPD5: Sometimes the best as QA
  • gpt-5-codex is strange, so i’am lazy to research him
  • Grok 4 Fast Reasoning is too lazy model; It is better to take gpt-5 or Grok Code Fast
  • UPD5 Haiku 4.5: The same or even more expensive than the gpt-5-high, but less intelligent. If you need Claude — take Sonnet.

Also, I’ve downgraded to Cursor v1.6.46, because Cursor v1.7.x ■■■■■.
UPD5: 2.0.x now

2 Likes