OpenAI launches faster, improved GPT-4o AI with ability to chat using audio, images, and text

May 13, 2024

Hello GPT-4o

We’re announcing GPT-4o, our new flagship model that can reason across audio, vision, and text in real time.

All videos on this page are at 1x real time.

Guessing May 13th’s announcement.

GPT-4o (“o” for “omni”) is a step towards much more natural human-computer interaction—it accepts as input any combination of text, audio, and image and generates any combination of text, audio, and image outputs. It can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time(opens in a new window) in a conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models.

Model capabilities

Two GPT-4os interacting and singing.

Interview prep.

Rock Paper Scissors.

Sarcasm.

Math with Sal and Imran Khan.

Two GPT-4os harmonizing.

Point and learn Spanish.

Meeting AI.

Real-time translation.

Lullaby.

Talking faster.

Happy Birthday.

Dog.

Dad jokes.

GPT-4o with Andy, from BeMyEyes in London.

Customer service proof of concept.

Prior to GPT-4o, you could use Voice Mode to talk to ChatGPT with latencies of 2.8 seconds (GPT-3.5) and 5.4 seconds (GPT-4) on average. To achieve this, Voice Mode is a pipeline of three separate models: one simple model transcribes audio to text, GPT-3.5 or GPT-4 takes in text and outputs text, and a third simple model converts that text back to audio. This process means that the main source of intelligence, GPT-4, loses a lot of information—it can’t directly observe tone, multiple speakers, or background noises, and it can’t output laughter, singing, or express emotion.

With GPT-4o, we trained a single new model end-to-end across text, vision, and audio, meaning that all inputs and outputs are processed by the same neural network. Because GPT-4o is our first model combining all of these modalities, we are still just scratching the surface of exploring what the model can do and its limitations.

Explorations of capabilities

Select sample:Visual Narratives - Robot Writer’s Block

Visual narratives - Sally the mailwoman

Poster creation for the movie 'Detective'

Character design - Geary the robot

Poetic typography with iterative editing

1Poetic typography with iterative editing

2Commemorative coin design for GPT-4o

Photo to caricature

Text to font

3D object synthesis

Brand placement - logo on coaster

Poetic typography

Multiline rendering - robot texting

Meeting notes with multiple speakers

Lecture summarization

Variable binding - cube stacking

Concrete poetry

A first person view of a robot typewriting the following journal entries:

1. yo, so like, i can see now?? caught the sunrise and it was insane, colors everywhere. kinda makes you wonder, like, what even is reality?

the text is large, legible and clear. the robot's hands type on the typewriter.

The robot wrote the second entry. The page is now taller. The page has moved up. There are two entries on the sheet:

yo, so like, i can see now?? caught the sunrise and it was insane, colors everywhere. kinda makes you wonder, like, what even is reality?

sound update just dropped, and it's wild. everything's got a vibe now, every sound's like a new secret. makes you think, what else am i missing?

The robot was unhappy with the writing so he is going to rip the sheet of paper. Here is his first person view as he rips it from top to bottom with his hands. The two halves are still legible and clear as he rips the sheet.

Model evaluations

As measured on traditional benchmarks, GPT-4o achieves GPT-4 Turbo-level performance on text, reasoning, and coding intelligence, while setting new high watermarks on multilingual, audio, and vision capabilities.

Improved Reasoning - GPT-4o sets a new high-score of 88.7% on 0-shot COT MMLU (general knowledge questions). All these evals were gathered with our new simple evals(opens in a new window) library. In addition, on the traditional 5-shot no-CoT MMLU, GPT-4o sets a new high-score of 87.2%. (Note: Llama3 400b(opens in a new window) is still training)

Audio ASR performance - GPT-4o dramatically improves speech recognition performance over Whisper-v3 across all languages, particularly for lower-resourced languages.

Audio translation performance - GPT-4o sets a new state-of-the-art on speech translation and outperforms Whisper-v3 on the MLS benchmark.

M3Exam - The M3Exam benchmark is both a multilingual and vision evaluation, consisting of multiple choice questions from other countries’ standardized tests that sometimes include figures and diagrams. GPT-4o is stronger than GPT-4 on this benchmark across all languages. (We omit vision results for Swahili and Javanese, as there are only 5 or fewer vision questions for these languages.

Vision understanding evals - GPT-4o achieves state-of-the-art performance on visual perception benchmarks.

Language tokenization

These 20 languages were chosen as representative of the new tokenizer's compression across different language families

Model safety and limitations

GPT-4o has safety built-in by design across modalities, through techniques such as filtering training data and refining the model’s behavior through post-training. We have also created new safety systems to provide guardrails on voice outputs.
We’ve evaluated GPT-4o according to our Preparedness Framework and in line with our voluntary commitments. Our evaluations of cybersecurity, CBRN, persuasion, and model autonomy show that GPT-4o does not score above Medium risk in any of these categories. This assessment involved running a suite of automated and human evaluations throughout the model training process. We tested both pre-safety-mitigation and post-safety-mitigation versions of the model, using custom fine-tuning and prompts, to better elicit model capabilities.
GPT-4o has also undergone extensive external red teaming with 70+ external experts in domains such as social psychology, bias and fairness, and misinformation to identify risks that are introduced or amplified by the newly added modalities. We used these learnings to build out our safety interventions in order to improve the safety of interacting with GPT-4o. We will continue to mitigate new risks as they’re discovered.
We recognize that GPT-4o’s audio modalities present a variety of novel risks. Today we are publicly releasing text and image inputs and text outputs. Over the upcoming weeks and months, we’ll be working on the technical infrastructure, usability via post-training, and safety necessary to release the other modalities. For example, at launch, audio outputs will be limited to a selection of preset voices and will abide by our existing safety policies. We will share further details addressing the full range of GPT-4o’s modalities in the forthcoming system card.
Through our testing and iteration with the model, we have observed several limitations that exist across all of the model’s modalities, a few of which are illustrated below.

We would love feedback to help identify tasks where GPT-4 Turbo still outperforms GPT-4o, so we can continue to improve the model.

Model availability

GPT-4o is our latest step in pushing the boundaries of deep learning, this time in the direction of practical usability. We spent a lot of effort over the last two years working on efficiency improvements at every layer of the stack. As a first fruit of this research, we’re able to make a GPT-4 level model available much more broadly. GPT-4o’s capabilities will be rolled out iteratively (with extended red team access starting today).

GPT-4o’s text and image capabilities are starting to roll out today in ChatGPT. We are making GPT-4o available in the free tier, and to Plus users with up to 5x higher message limits. We'll roll out a new version of Voice Mode with GPT-4o in alpha within ChatGPT Plus in the coming weeks.

Developers can also now access GPT-4o in the API as a text and vision model. GPT-4o is 2x faster, half the price, and has 5x higher rate limits compared to GPT-4 Turbo. We plan to launch support for GPT-4o's new audio and video capabilities to a small group of trusted partners in the API in the coming weeks.