The Continuity Layer
← OpenAI Codex, every test with the source
Alternatives · Coding agents

OpenAI Codex alternatives, graded

thecontinuitylayer.com/alternatives/openai-codex

One of the 7 coding agents on the record scores higher than OpenAI Codex's 7 of 8 (grade A−): Claude Code (7½, A), Cline (7, A−), Windsurf (now Devin Desktop) (6½, B+) lead the ranking. Every grade is read from the maker's own page, checked 3 November 2026, never from a review.

A−
OpenAI Codex · 7 of 8
7
coding agents to compare
1
score higher
3 November 2026
Makers' pages checked

Every coding agent on the record, ranked

OpenAI Codex’s own row is shaded. The five columns are the tests a person switching asks about first; each product page has every test, with the maker’s line and the source. Where the test is about training, no is the good answer and is colored as such.

coding agentGradeRemembersYour filePortableTrainingPrice
Claude Code#1 · AnthropicA7½/8
OpenAI Codex#2 · OpenAI · this oneA−7/8
Cline#3 · Cline Bot Inc.A−7/8
Windsurf (now Devin Desktop)#4 · CognitionB+6½/8
Gemini CLI#5 · GoogleB+6½/8
Aider#6 · Aider-AIB+6½/8
Cursor#7 · AnysphereB6/8
GitHub Copilot#8 · GitHub (Microsoft)B6/8
  • Remembers · Does it remember across sessions?
  • Your file · Does it keep memory in a file you own?
  • Portable · Does it read a format other tools read?
  • Training · Does it use your code for training by default?
  • Price · What does it cost?

OpenAI Codex alternatives, by what matters

5 coding agents that keep memory in a file you own

  1. A Claude Code
  2. A− Cline
  3. B+ Windsurf (now Devin Desktop)
  4. B+ Gemini CLI
  5. B+ Aider

OpenAI Codex passes this test too.

The one coding agent that don't use your code for training by default

  1. B+ Aider

OpenAI Codex's grade on this test: partly.

6 coding agents that read a format other tools read

  1. A Claude Code
  2. A− Cline
  3. B+ Windsurf (now Devin Desktop)
  4. B+ Gemini CLI
  5. B Cursor
  6. B GitHub Copilot

OpenAI Codex passes this test too.

What OpenAI changed lately

  1. From December 2026, ChatGPT and Codex draw from one shared usage allowance on Plus, Pro and Business plans, measured in tokens; Instant chat does not count against it. People who hit the limit wait for the reset, upgrade, or buy credits. No token figures are published.

    source

  2. Existing $200 ChatGPT Pro subscribers move to the lower usage allowance that new Pro 200 subscriptions get, at the same $200 price, after keeping the old allowance through October 29. A new Pro 500 plan has the highest included usage; see OpenAI's pricing page.

    source

  3. ChatGPT removed the fixed cap on how many Sites Plus and Pro users can create. Usage and storage limits still apply.

    source

Every change from OpenAI, dated →

Alternatives to the others

The whole shelf: Coding agents. How the grades are made: How we grade. No maker pays for a place or a grade.