ARC Prize:
o3, trained on ARC-AGI-1 Public Training set, scored 75.7% on ARC Prize's Semi-Private Evaluation at the $10k compute limit; a 172x compute version scored 87.5% — OpenAI's new o3 system - trained on the ARC-AGI-1 Public Training set - has scored a breakthrough 75.7% on the Semi-Private Evaluation set …
ARC Prize:
o3, trained on ARC-AGI-1 Public Training set, scored 75.7% on ARC Prize's Semi-Private Evaluation at the $10k compute limit; a 172x compute version scored 87.5% — OpenAI's new o3 system - trained on the ARC-AGI-1 Public Training set - has scored a breakthrough 75.7% on the Semi-Private Evaluation set …
Source: TechMeme
Source Link: http://www.techmeme.com/241220/p18#a241220p18