### Answer Based on the available sources, I have limited real user call experience comparisons between GPT-5.2 and GPT-5.1 specifically. Here's what I found: ## GPT-5.2 User Experiences One user reported that their "first attempt using GPT 5.2 resulted in the agent reading back XML data with chinese characters" and would "not recommend it at this time." [(1) ]() Another community member stated they "didn't receive any issue about GPT 5.2 but it's still new." ## GPT-5 Issues (Not 5.1 or 5.2 Specifically) There was a reported issue with GPT-5 where the AI Voice Agent would "get stuck repeating the same question in a loop during the question phase, even after the user answered." ## Community Recommendation A community member recommended staying with GPT-4.1, stating it's "the most stable one currently." ## Available Models Both

gpt-5

and

gpt-5.2

are listed as available model options in Retell AI, along with

gpt-5.1

,

gpt-5-mini

, and

gpt-5-nano

. [(2) ]() --- I don't have specific documented comparisons of real user call experiences between GPT-5.1 and GPT-5.2. For more detailed performance feedback, you may want to: - Visit [Documentation]() - Visit [Hire certified Retell partner]() Would you like a general answer based on broader AI model knowledge instead?

​ To learn more, see the sources I considered: [[1] Agent reading JSON extract to callers](https://community.retellai.com/t/agent-reading-json-extract-to-callers/229) [[2] List Retell LLMs](https://docs.retellai.com/api-references/list-retell-llms) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.