NishMath

OpenAI has released its new O3 model which demonstrates significantly improved performance in reasoning, coding, and mathematical problem-solving compared to its previous models. The O3 model achieves 75.7% on the ARC Prize Semi-Private Evaluation in low-compute mode and an impressive 87.5% in high-compute mode. However, this performance comes at a very high cost, with the top-end system costing around $10,000 per task which makes it very expensive to run.

ImgSrc: assets.bwbx.io

References:

• Simon Willison's Weblog - OpenAI o3 breakthrough high score on ARC-AGI-PUB - 16d
• Ars Technica - All content - ArsTechnica article on OpenAI o3 and o3-mini - 16d
• TechCrunch - Techcrunch article about OpenAI new o3 model - 16d
• THE DECODER - The Decoder article about OpenAI o3 models - 16d
• www.heise.de - Heise Online news about OpenAI o3 models - 16d
• NextBigFuture.com - OpenAI o3 sets new records in several key areas, particularly in reasoning, coding and mathematical problem-solving. It scores 75.7% on the semi-private eval in low-compute mode (for $20 per task in c - 16d
• arcprize.org - OpenAI o3 87.5% High Score on ARC Prize Challenge - 16d
• @julianharris.bsky.social - Julian Harris - OpenAI announced o3 that is significantly better than previous systems, according to an independent benchmark org (The Arc Prize) that apparently got access. Only thing is it’s wildly wildly expensi - 15d
• shellypalmer.com - OpenAI’s o3: Progress Toward AGI or Just More Hype? - 13d
• pub.towardsai.net - OpenAI’s O3: A New Frontier in AI Reasoning Models - 13d
• MarkTechPost - OpenAI Announces OpenAI o3: A Measured Advancement in AI Reasoning with 87.5% Score on Arc AGI Benchmarks - 13d
• www.marktechpost.com - OpenAI Announces OpenAI o3: A Measured Advancement in AI Reasoning with 87.5% Score on Arc AGI Benchmarks - 13d
• Research & Development World - Just how big of a deal is OpenAI’s o3 model anyway? - 13d
• Shelly Palmer - OpenAI’s o3: Progress Toward AGI or Just More Hype? - 12d
• NextBigFuture.com - OpenAI O3 Crushes Benchmark Tests But is it Intelligence ? - 12d
• AI News | VentureBeat - OpenAI’s o3 shows remarkable progress on ARC-AGI, sparking debate on AI reasoning - 11d
• Analytics India Magazine - OpenAI soft-launches AGI with o3 models, Enters Next Phase of AI. The company cracked the ARC-AGI benchmark in just five years. - 11d

Classification:

• HashTags: OpenAIO3 AIMath HighCostAI
• Company: OpenAI
• Target:
• Attacker:
• Product: o3
• Feature: reasoning
• Type: AI
• Severity: Major