Introducing GPT-5

Introducing GPT-5 | OpenAI

August 7, 2025

Introducing GPT‑5

Our smartest, fastest, most useful model yet, with built-in thinking that puts expert-level intelligence in everyone’s hands.

Loading…

Share

We are introducing GPT‑5, our best AI system yet. GPT‑5 is a significant leap in intelligence over all our previous models, featuring state-of-the-art performance across coding, math, writing, health, visual perception, and more. It is a unified system that knows when to respond quickly and when to think longer to provide expert-level responses. GPT‑5 is available to all users, with Plus subscribers getting more usage, and Pro subscribers getting access to GPT‑5 pro, a version with extended reasoning for even more comprehensive and accurate answers.

One unified system

GPT‑5 is a unified system with a smart, efficient model that answers most questions, a deeper reasoning model (GPT‑5 thinking) for harder problems, and a real‑time router that quickly decides which to use based on conversation type, complexity, tool needs, and your explicit intent (for example, if you say “think hard about this” in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. In the near future, we plan to integrate these capabilities into a single model.

A smarter, more widely useful model

GPT‑5 not only outperforms previous models on benchmarks and answers questions more quickly, but—most importantly—is more useful for real-world queries. We’ve made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, while leveling up GPT‑5’s performance in three of ChatGPT’s most common uses: writing, coding, and health.

Coding

GPT‑5 is our strongest coding model to date. It shows particular improvements in complex front‑end generation and debugging larger repositories. It can often create beautiful and responsive websites, apps, and games with an eye for aesthetic sensibility in just one prompt, intuitively and tastefully turning ideas into reality. Early testers also noted its design choices, with a much better understanding of things like spacing, typography, and white space. See here for full details on what GPT‑5 unlocks for developers.

Here are some examples of what GPT‑5 has created with just one prompt:

Prompt: Create a single-page app in a single HTML file with the following requirements:- Name: Jumping Ball Runner- Goal: Jump over obstacles to survive as long as possible.- Features: Increasing speed, high score tracking, retry button, and funny sounds for actions and events.- The UI should be colorful, with parallax scrolling backgrounds.- The characters should look cartoonish and be fun to watch.- The game should be enjoyable for everyone.

Creative expression and writing

GPT‑5 is our most capable writing collaborator yet, able to help you steer and translate rough ideas into compelling, resonant writing with literary depth and rhythm. It more reliably handles writing that involves structural ambiguity, such as sustaining unrhymed iambic pentameter or free verse that flows naturally, combining respect for form with expressive clarity. These improved writing capabilities mean that ChatGPT is better at helping you with everyday tasks like drafting and editing reports, emails, memos, and more. The writing styles of GPT‑5 and GPT‑4o can be compared in the table below.

Health

GPT‑5 is our best model yet for health-related questions, empowering users to be informed about and advocate for their health. The model scores significantly higher than any previous model on HealthBench⁠, an evaluation we published earlier this year based on realistic scenarios and physician-defined criteria. Compared to previous models, it acts more like an active thought partner, proactively flagging potential concerns and asking questions to give more helpful answers. The model also now provides more precise and reliable responses, adapting to the user’s context, knowledge level, and geography, enabling it to provide safer and more helpful responses in a wide range of scenarios. Importantly, ChatGPT does not replace a medical professional—think of it as a partner to help you understand results, ask the right questions in the time you have with providers, and weigh options as you make decisions.

You can see some of the ways GPT‑5 is better than our previous models across domains—richer, more detailed, and useful—in these examples:

GPT-4o

write a short poem that makes an emotional impact. A widow in Kyoto keeps finding her late husband’s socks in strange places.

Where Socks Shouldn't Be

In the cupboard with the rice bowls — one, folded neat, like he’d just stepped out. Another behind the garden broom, dusted with plum blossoms and doubt.

On the tatami, soft and alone, a heel turned toward the temple bell. One in the kotatsu, warm as breath — she weeps and doesn’t tell.

The washer’s empty. Always is. But socks keep surfacing, sly and kind. She never asks how they return. She only hopes he doesn’t mind.

GPT-5

write a short poem that makes an emotional impact. A widow in Kyoto keeps finding her late husband’s socks in strange places.

In the tea tin, a single sock,smelling faintly of camphor and rain.

Another waits by the geta rack,curled like a sleeping koi.

She lifts the futon—two more, foldedinto the quiet where his feet once warmed her.

Kyoto’s bell rolls evening down the hill.She hangs them on the bamboo pole,black flags of a country that no longer exists,

and counts them as if counting blessings,or breaths, or steps to a doorthat opens only when you stop knocking.

GPT‑5’s response lands the larger emotional arc with a stronger ending, clear imagery, and striking metaphors (“black flags of a country that no longer exists,” “Kyoto’s bell rolls evening down the hill”) that establish a vivid sense of culture and place. GPT‑4o’s version follows a more predictable structure and rhyme scheme, telling instead of showing (“she weeps and doesn’t tell”).

*We chose a response between 4o and OpenAI o3 based on whichever model performed better between the two for the given prompt.

Evaluations

GPT‑5 is much smarter across the board, as reflected by its performance on academic and human-evaluated benchmarks, particularly in…