News from the AI & ML world
DeeperML
@www.theverge.com
//
OpenAI launched its latest model, o3-mini, last Friday, marking the debut of the o3 family of models. There are two specialized variants: o3-mini-high, which prioritizes in-depth answers and reasoning, and o3-mini-low, which focuses on faster responses. Benchmarks show o3-mini offers comparable performance to its predecessor, o1, at approximately 15 times cheaper and five times faster, positioning it as the best model based on cost-to-performance ratio currently available, especially with Deepseek r1 being primarily unavailable outside of China.
The o3-mini stands out as the only OpenAI model showcasing a chain of thought, although it is a summarized version of the actual reasoning process. It is also the first reasoning model to have function-calling support. The model has demonstrated superior scores compared to o1 on FrontierMath, Codeforces, and GPQA. OpenAI CEO Sam Altman suggests that merging larger pre-trained models with reasoning capabilities could unlock new scientific knowledge, overcoming the limitations of scaling through pre-training alone.
ImgSrc: platform.thever
References :
The o3-mini stands out as the only OpenAI model showcasing a chain of thought, although it is a summarized version of the actual reasoning process. It is also the first reasoning model to have function-calling support. The model has demonstrated superior scores compared to o1 on FrontierMath, Codeforces, and GPQA. OpenAI CEO Sam Altman suggests that merging larger pre-trained models with reasoning capabilities could unlock new scientific knowledge, overcoming the limitations of scaling through pre-training alone.
ImgSrc: platform.thever
Share:
References :
- techcrunch.com: OpenAI launches o3-mini, its latest reasoning model that it says is largely on par with o1 and o1-mini in capability, but runs faster and costs less (Kyle Wiggers/TechCrunch)
- www.theverge.com: O3-mini will be available to all ChatGPT users, the first time free users of the chatbot will be able to try out OpenAI's reasoning models (Tom Warren/The Verge)
- www.techmeme.com: O3-mini will be available to all ChatGPT users, the first time free users of the chatbot will be able to try out OpenAI's reasoning models (Tom Warren/The Verge)
- Techmeme: OpenAI's o3-mini is out today. As with other o-series models it's a slightly difficult one to evaluate …
- community.openai.com: OpenAI has launched o3-mini, a new reasoning model that offers improved performance over o1 while being significantly cheaper. This model supports various features and is available in the API, Assistants API, and Batch API.
- simonwillison.net: OpenAI's o3-mini is out today and offers a lower cost and faster performance than GPT-4o and o1, costing $1.10 per 1M input tokens and $4.40 per 1M output tokens.
- Composio: OpenAI launched its latest model, the o3-mini, last Friday.
- AI News | VentureBeat: OpenAI is now showing more details of the reasoning process of o3-mini, its latest reasoning model.
- Analytics Vidhya: OpenAI’s o3- mini is not even a week old and it’s already a favorite amongst ChatGPT users.
- composio.dev: A blog post comparing OpenAI's o3-mini model to DeepSeek R1.