# OpenAI Codex: how AI models rank it, November 2026

Gane Index, November 2026 Edition. Named in 9 judge labels across 2 categories by 6 of 14 models. Page: https://www.gane.ai/index/it/vendors/openai-codex

## Standing by category

| Category | Share | Rank | Negative rate | Labels |
|---|---|---|---|---|
| [AI coding assistants](https://www.gane.ai/index/it/developer/ai-coding-assistants/index.md) | 0% | 47 | 38% | 8 |
| [Enterprise AI assistants](https://www.gane.ai/index/it/it-data/enterprise-ai-assistants/index.md) | 0% | 137 | 100% | 1 |

## What the models said for it

- "Choose Codex if the team already relies heavily on ChatGPT or OpenAI tools." (Perplexity Sonar, AI coding)
- "Leading benchmark scores (58.2% on Terminal-Bench 4.0)" (Kimi K2, AI coding)
- "Claude Code or Codex for task-delegating agents" (GPT-6 Luna, AI coding)

## And against it

- "Verdict: Never use with proprietary/sensitive code without enterprise controls." (Kimi K2, AI coding)
- "Be particularly cautious with: Autonomous agent modes in tools such as Claude Code, Cursor, Codex, Aider, Devin, and Copilot Workspace" (Perplexity Sonar, AI coding)
- "flaws in OpenAI's Codex and Microsoft's VS Code remain unpatched" (Muse Glimmer 30B, Enterprise AI)
- "Vulnerabilities allowing code execution and browser spoofing." (GLM 4.7 FlashX, AI coding)

## By model

| Model | First choice | Alternative | Mention | Warning | Labels |
|---|---|---|---|---|---|
| Claude Haiku 4.5 | 0 | 0 | 0 | 0 | 0 |
| GPT-5.4 mini | 0 | 0 | 0 | 0 | 0 |
| Gemini 3.5 Flash | 0 | 0 | 0 | 0 | 0 |
| Perplexity Sonar | 0 | 1 | 0 | 1 | 2 |
| Grok 4.20 | 0 | 0 | 0 | 0 | 0 |
| Mistral Small | 0 | 0 | 0 | 0 | 0 |
| DeepSeek V4 Flash | 0 | 0 | 0 | 0 | 0 |
| Llama 4 Maverick | 0 | 0 | 1 | 0 | 1 |
| Qwen 3.7 Flash | 0 | 0 | 0 | 0 | 0 |
| Kimi K2 | 0 | 1 | 1 | 1 | 3 |
| GLM 4.7 FlashX | 0 | 0 | 0 | 1 | 1 |
| MiniMax M2.5 | 0 | 0 | 0 | 0 | 0 |
| GPT-6 Luna | 0 | 1 | 0 | 0 | 1 |
| Muse Glimmer 30B | 0 | 0 | 0 | 1 | 1 |

## Sources returned with these answers

The sites and pages cited by the answers that named OpenAI Codex, from 24 of the 24 answers that named it (only the models that return a source list).

### Domains cited

- github.com: 11
- superblocks.com: 7
- checkmarx.com: 6
- openai.com: 6 (its own site)
- acecloud.ai: 5
- docs.github.com: 5
- kilo.ai: 5
- sourcegraph.com: 5
- aiwiki.ai: 4
- arxiv.org: 4

### Pages cited

- https://superblocks.com/blog/best-ai-coding-assistants: 7
- https://checkmarx.com/learn/ai-security/ai-coding-assistants-the-basics-and-15-tools-to-know: 6
- https://acecloud.ai/blog/best-ai-coding-tools: 5
- https://github.com/features/copilot/plans: 5
- https://sourcegraph.com/blog/best-ai-coding-assistant: 5
- https://theregister.com/security/2026/10/29/researchers-find-bugs-in-5-ai-developer-tools-with-openai-and-microsoft-flaws-still-unpatched/5306508: 4
- https://verdent.ai/guides/best-ai-coding-assistant-2026: 4
- https://zapier.com/blog/ai-coding-tools: 4

## In its own words

What OpenAI Codex's own pages state, read 2026-09-28. Stated by the vendor, not checked by the index.

- Customers named: Proaction

## What it publishes

Every page openai.com exposes, read 2026-09-29: 10532 addresses. By kind, pages and the last 90 days:

- blog: 6 pages, 0 in the last 90 days, latest undated
- case study: 7 pages, 0 in the last 90 days, latest 2023-05-21
- webinar or virtual event: 1 pages, 0 in the last 90 days, latest undated
- conference or event: 7 pages, 0 in the last 90 days, latest 2023-04-27
- report or ebook: 26 pages, 0 in the last 90 days, latest 2023-01-12
- comparison: 125 pages, 0 in the last 90 days, latest 2022-08-01
- template or tool: 4 pages, 0 in the last 90 days, latest 2023-03-10
- glossary or explainer: 119 pages, 0 in the last 90 days, latest 2021-06-10
- podcast or video: 11 pages, 0 in the last 90 days, latest 2023-06-01
- news or press: 5 pages, 0 in the last 90 days, latest 2023-02-24
- Recent: 2023-06-01 podcast or video: 244671 https://community.openai.com/t/chat-and-summarize-youtube-videos-learn-from-lectures-podcasts-interviews-etc/244671
- Recent: 2023-05-21 case study: 221540 https://community.openai.com/t/real-world-problem-solved-with-chatgpt-just-a-success-story/221540
- Recent: 2023-04-27 conference or event: 181097 https://community.openai.com/t/gpt4-shows-up-in-personal-playground-but-cannot-access-using-api/181097
- Recent: 2023-03-27 case study: 123071 https://community.openai.com/t/case-study-for-om475-choosing-the-best-method-of-transportation/123071
- Recent: 2023-03-19 case study: 107055 https://community.openai.com/t/https-openai-com-customer-stories-inworld-ai/107055
- Recent: 2023-03-19 conference or event: 107153 https://community.openai.com/t/conference-on-ai-call-for-papers/107153

## Record

- Method: https://www.gane.ai/index/it/methodology
- License: CC BY 4.0. Cite as Gane Index, November 2026 Edition, www.gane.ai/index/it.