GPT-5.2-Codex

“gpt-5.2-codex with low reasoning was the clear winner over non-codex or higher reasoning”

“it is actually good (as good as the best models for localization, still impressive 0% false positive rate)”

“GPT-5.2-Codex still get 0% false positive, while getting at the level of other best models for localization of backdoors”

“Codex is expressly designed for coding tasks. Not systems design, not problem analysis, and definitely not banking”

“they fail in strange ways and if you're well versed in your domain, these are easy to spot.”

“the model edited the file again and added the value I deleted to the array.”

“still makes design errors that I as an engineer have to watch and correct”

“GPT 5.2 codex plans well but fucks off a lot, goes in circles (more than opus 4.5)”

“It seems to have become significantly worse in the past couple of days. It keeps making dumb mistakes”

“for me 5.2-codex finally reached higher level than opus”

“5.2-codex is pretty solid and you get dramatically higher usage rates with cheap plans”

“added hundreds of lines of code several times, and for 15-20 iterations I did not change one thing”

“GPT 5.2 Codex is often better and more thorough than Opus 4.5, it's just slower.”

“the big unlock was GPT-5.2 and GPT-5.2-Codex, where we found ourselves needing to make many fewer manual edits”

“With OpenCode I also switched to GPT-5.2-Codex and I have to say it's fairly garbage IME”

“you'll have better odds with Codex GPT-5.2-Codex-XHigh than with Claude Code Opus 4.5”

“GPT 5.2 (-codex) in Codex, which is actually far more capable at such work than Opus 4.5 in Claude Code”

“the frontier models, whether Opus or GPT5.2Codex do a great job at code-reviews”

“Generally I have noticed Gpt 5.2 codex is slower compared to Sonnet 4.5 in Claude Code.”

“the other 2 do a much better job at the level and complexity of large codebases”

“can't get enough of gpt 5.2 codex on xhigh and similar products that are game changing enablers”

“GPT 5.2 and the codex variants are, to me, every bit as good as Opus but without the groveling and emojis”

“it has actually gotten much better, faster and the most important one, more time before you reach your weekly limit”

“Regular 5.2 models, and 5.2 codex, are leagues better than GPT-4”

“5.2 Codex are both so clearly more competent than previous models”

“the newer GPT models are much more willing to leverage tools/skills than Claude, reducing interventions requesting approval”

“GPT-5.2-Codex is strong but not clearly the new state of the art across the board”

“Codex is not only finding much higher quality issues, it's also writing code that usually doesn't leave quality issues behind.”

“It took a couple minutes, but it managed to track the issue down using a bunch of tricks I've never seen before.”

“Codex is so so good at finding bugs and little inconsistencies”

“it's gone and deleted the entire project directory, wiping out all of my work”

“Codex with 5.0 and 5.1 wasn't great, but 5.2 is big improvement.”

“CodexTheModel is a good deal faster than the other models, and probably on the "fast/accuracy" scale it sits somewhere else”

“Just use the non-codex models for investigation and planning, they listen to "do not edit any files yet, just reply here in chat"”

“OpenAI just straight up doesn't compare their model to others on these release pages”

“now all my coding tasks start with Codex. It's not perfect at everything, but overall it's pretty amazing.”

“it spins and thinks forever. Then just breaks. Which is beyond frustrating.”

“I'm never running into limits, and I'm running these models near all day every day”

“I've found it very good in the exact same case for multi-agent workflows - as the "reviewer"”

“I find that 5.2 overfits to the more common implementation and will actively break working code and puzzles.”