GPT-5.1-Codex-Max
Ranked 9 of 15 coding models by recommenders
Praised for web development, debugging and multi-step refactors. Common caveat: it is slow and weak outside web development.
Praised for web development, debugging and multi-step refactors. Common caveat: it is slow and weak outside web development.
49 people gave an opinion
- recommend it
- 30
- criticize it
- 19
- approval share
- 61%
Recommended in 5 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 30 people recommend itNeeds 10 or more, met.
- 1.5 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong at debugging problems
“I've used max in problem sets as diverse as "troubleshooting Cyberpunk mods" and figuring out a race condition in a server backend.”
Comment from 11 Dec 2025 in “GPT-5.2” “opus-4.5 and gpt-5.1-codex-max are perhaps better than me at debugging”
Comment from 7 Dec 2025 in “Using LLMs at Oxide” “Codex Max solved a problem I had Claude Code fail multiple times.”
Comment from 19 Nov 2025 in “Building more with GPT-5.1-Codex-Max” Good at web development
“I've found models (codex-5.1-max, opus 4.5) to be absolutely useless writing shaders or ML training code, but really good at basic web development.”
Comment from 11 Dec 2025 in “GPT-5.2” “I was especially impressed by 5.1-codex-max for a webapp”
Comment from 27 Jan 2026 in “Qwen3-Max-Thinking” Completes tasks others cannot
“there are some tasks Opus can't do at all which Codex has no problem with”
Comment from 8 Dec 2025 in “Alignment is capability” “Codex Max solved a problem I had Claude Code fail multiple times.”
Comment from 19 Nov 2025 in “Building more with GPT-5.1-Codex-Max” Efficient token use
“30% more token-efficient at the same reasoning level across many tasks”
Comment from 19 Nov 2025 in “Building more with GPT-5.1-Codex-Max” “you can get much more mileage out of them due to post-training”
Comment from 26 Nov 2025 in “Gemini CLI tips and tricks for agentic coding”
What people warn about
Each mark is one comment
Slow, long waits for results
“it completed 10 of 10 but took perhaps 5-10x as long”
Comment from 23 Jan 2026 in “I was banned from Claude for scaffolding a Claude.md file” “If I have to wait 20 minutes for GPT-5.1-codex-max medium to look at git diff and give a paltry and inaccurate summary”
Comment from 24 Nov 2025 in “Claude Opus 4.5” “It can churn for hours and get one test working, or churn for hours and fail.”
Comment from 29 Jan 2026 in “Ask HN: Why all the sudden people are writing browsers with AI?” - Comment from 19 Nov 2025 in “Building more with GPT-5.1-Codex-Max”
Weak outside web development
“I've found models (codex-5.1-max, opus 4.5) to be absolutely useless writing shaders or ML training code, but really good at basic web development.”
Comment from 11 Dec 2025 in “GPT-5.2” “These things are infuriatingly bad as soon as you move away from things like web development.”
Comment from 14 Jan 2026 in “Provenance Is the New Version Control” Poor code quality and approaches
“if you bother to watch what it does and read its code the approaches it takes are absolutely horrifying”
Comment from 19 Nov 2025 in “Building more with GPT-5.1-Codex-Max” “codex didn’t adhere to codebase standards for me and the code quality was worse (very defensive)”
Comment from 19 Nov 2025 in “Building more with GPT-5.1-Codex-Max” “I've actually gotten worse results with xhigh than high with gpt-5.1-codex-max”
Comment from 11 Dec 2025 in “GPT-5.2”
Other coding models people recommend
The four most recommended other coding models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Cursor Composer | 214 | 79 | 73% | 12 | 1 mo11 owners | Approved |
| Qwen3-Coder | 165 | 49 | 77% | 12 | 2 mo7 owners | Approved |
| GPT-5.3-Codex | 135 | 78 | 63% | 11 | 2 mo4 owners | — |
| Meta Muse Glimmer 30B | 70 | 18 | 80% | 3 | — | — |
| GPT-5.1-Codex-MaxThis page | 30 | 19 | 61% | 5 | — | — |
What people said
40 of the 53 comments that mention it, newest first. Each links to the original comment.
“That is cheaper than Cursor if you use it a lot.”
“it feels like a nice speed while still being effective”
“GPT5.2-codex-max and Opus 4.5 Thinking are decent at long context now”
“It can churn for hours and get one test working, or churn for hours and fail.”
“I was especially impressed by 5.1-codex-max for a webapp”
“it completed 10 of 10 but took perhaps 5-10x as long”
“which has the new compaction algorithm that gpt-5.2-codex seems to lack”
“These things are infuriatingly bad as soon as you move away from things like web development.”
“but it seems to be missing something crucial”
“LLMS like Opus, Gemini 3, and GPT-5.2/5.1-Codex-max, are phenomenal for coding”
“we can write substantial programs one-shot from a single prompt and they work”
“I really like the interaction flows better than Gemini 3 or Codex”
“I've observed better code quality from codex”
“I've used max in problem sets as diverse as "troubleshooting Cyberpunk mods" and figuring out a race condition in a server backend.”
“To the point that I switched back to just 5.1 High from 5.1 Codex Max.”
“I've actually gotten worse results with xhigh than high with gpt-5.1-codex-max”
“I've found models (codex-5.1-max, opus 4.5) to be absolutely useless writing shaders or ML training code, but really good at basic web development.”
“is actually very good once I access it via the OpenAI Codex extension installed within Cursor”
“there are some tasks Opus can't do at all which Codex has no problem with”
“opus-4.5 and gpt-5.1-codex-max are perhaps better than me at debugging”
“5.1 Max, Opus 4.5, and G3 are absolutely astounding models”
“you can get much more mileage out of them due to post-training”
“If I have to wait 20 minutes for GPT-5.1-codex-max medium to look at git diff and give a paltry and inaccurate summary”
“especially now with Codex Max, as it has been much better at not getting stuck like this”
“seems to handle multi-step refactors a lot more cleanly”
“We have trained this model on Windows (our first model to do so). Give it a try!”
“it'll spend ten minutes and come back with "OK I've implemented a solution"”
“Codex Max solved a problem I had Claude Code fail multiple times.”
“the automatic compacting is months overdue so happy to see it finally come”
“I walked away from Codex, and when I came back, it had installed 2 new node packages”
“Overall, Codex was the clear winner today.”
“they only share three hand-picked evals, ignoring the evals where they were left in the dust”
“GPT 5.1 / Codex already beats Gemini 3 on SWE Bench Verified and Terminal Bench and this pushes the gap further. Seems like a decent improvement.”
“these things are actually fixable with prompting”
“It’s good but Gemini 3 beats it.”
“codex didn’t adhere to codebase standards for me and the code quality was worse (very defensive)”
“30% more token-efficient at the same reasoning level across many tasks”
“if you bother to watch what it does and read its code the approaches it takes are absolutely horrifying”
“It’s been the shorter form work that has built what little confidence I have in these as a coding partner”
“lot of us ended up downgrading to codex 5.0 because of the token burn was too much”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.