OpenAI's New GPT-5.1 Models are Faster and More Conversational

OpenAI recently released upgrades to their GPT-5 model. GPT‑5.1 Instantthe default chat modelhas improvements to instruction following. GPT‑5.1 Thinkingthe reasoning modelis faster and gives more understandable responses. GPT‑5.1-Codex-Maxthe coding modelis trained to use compaction to perform long-running tasks.

The Instant and Thinking models are used in the ChatGPT applicationand are chosen automatically by an auto-routing model. OpenAI says that users wanted models that are enjoyable to talk toleading the company to change their models' default response . The new release also includes more customization control over chat tone and . ChatGPT already had several preset sand the release includes three new s: QuirkyCandidand Professional. Users can also tweak response with personalization settings and custom instructions.

OpenAI's rollout of GPT-5 earlier this year ignited a controversy when they removed the option to choose older modelsbreaking many user workflows. While the company continues to have ChatGPT automatically choose the best model for a chatOpenAI reversed its plan to immediately deprecate older models. According to OpenAI:

Going forwardwhen we introduce new ChatGPT modelsour approach is to give people ample space to evaluate what’s changed and share feedbackallowing us to continue innovating our frontier models while transitioning smoothly. Sunset periods will be communicated clearly and with plenty of advance notice.

The updates to the model's response settings were part of OpenAI's effort to make it easier for users to make ChatGPT's personality "[feel] uniquely right." The company says that the preset response s were developed based on "what we’ve learned about how people naturally steer the model." While the presets were rolled out to everyone with the releasethe fine-tuning settings are being released to a few users at a timeas an experiment. 

Several Hacker News users were not impressed with the conversational tone of the modelexpressing a preference for more terse responses. One user pointed out that the "Efficient" (formerly "Robot") preset was intended for this. Another wrote:

Seems like people here are pretty negative towards a "conversational" AI chatbot. ChatGPT has a lot of frustrations and ethical concernsand I hate the sycophancy as much as everyone elsebut I don't consider being conversational to be a bad thing. It's just preference I guess.

GPT‑5.1-Codex-Max is an improved version of OpenAI's GPT‑5.1-Codex coding model. In tests on the SWE-bench Verified benchmarkGPT‑5.1-Codex-Max outperformed the previous model while using fewer reasoning tokens. The model also has an Extra High (xhigh) reasoning effort levelin addition to the previous lowmediumand high levels.

GPT-5.1-Codex-Max Benchmark Performance. Image Source: OpenAI Blog

Hacker News users also discussed GPT‑5.1-Codex-Max:

Codex CLI is great and I use it often but I'd like to have more of these convenient features for managing context from CC. I'm super happy that compaction is now availablehopefully we'll get more features for managing context.

Another user said:

It would be great to have access to this model via the chat interfaceeven if it was gated behind the "other models" dropdown or something.

The new Codex model is available in the Codex CLI and several IDE extensions. API access is "coming soon."