This is an old revision of this page, as edited by Xoontor (talk | contribs) at 12:11, 26 December 2024 (infobox software). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.
Revision as of 12:11, 26 December 2024 by Xoontor (talk | contribs) (infobox software)(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff) Large language model| Developer(s) | OpenAI |
|---|---|
| Predecessor | OpenAI o1 |
| Type | Generative pre-trained transformer |
OpenAI o3 is a generative pre-trained transformer (GPT) model developed by OpenAI as a successor to the OpenAI o1 model. It is designed to devote additional deliberation time when addressing questions that require step-by-step logical reasoning.
History
The OpenAI o3 model was announced on December 20, 2024, with the designation "o3" chosen to avoid trademark conflict with the existing UK mobile carrier named O2. The model is available in two versions: o3 and o3-mini. Until January 10, 2025, OpenAI invites safety and security researchers to apply for early access of these models. OpenAI plans to release o3-mini to the public in January 2025.
Capabilities
Reinforcement learning was used to teach o3 to "think" before generating answers, using what OpenAI refers to as a "private chain of thought". This approach enables the model to plan ahead and reason through tasks, performing a series of intermediate reasoning steps to assist in solving the problem, at the cost of needing additional compute and increasing the latency of responses.
o3 demonstrates improved performance compared to o1 in complex tasks, including coding, mathematics, and science. OpenAI reported that o3 achieved a score of 87.7% on the GPQA Diamond benchmark, which contains expert-level science questions not publicly available online.
On SWE-bench Verified, a software engineering benchmark assessing the ability to solve real GitHub issues, o3 scored 71.7%, compared to 48.9% for o1. On Codeforces, o3 reached an Elo score of 2727, whereas o1 obtained 1891.
On the ARC-AGI benchmark, which evaluates an AI's ability to handle new, challenging mathematical and logical problems, o3 attained three times the accuracy of o1.
References
- ^ Knight, Will (December 20, 2024). "OpenAI Upgrades Its Smartest AI Model With Improved Reasoning Skills". Wired.
- "OpenAI Unveils New A.l. That Can 'Reason' Through Math and Science Problems". The New York Times. 2024-12-20.
- "Early access for safety testing". OpenAI. December 20, 2024.
- Edwards, Benj (December 20, 2024). "OpenAI announces o3 and o3-mini, its next simulated reasoning models". Ars Technica.
- Zeff, Maxwell; Wiggers, Kyle (2024-12-20). "OpenAI announces new o3 models". TechCrunch. Retrieved 2024-12-22.
- ^ Franzen, Carl; David, Emilia (2024-12-20). "OpenAI confirms new frontier models o3 and o3-mini". VentureBeat. Retrieved 2024-12-26.
- Hsu, Jeremy. "OpenAI's o3 model aced a test of AI reasoning – but it's still not AGI". New Scientist. Retrieved 2024-12-22.
| OpenAI | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Products | |||||||||
| Foundation models | |||||||||
| People |
| ||||||||
| Related | |||||||||
