Skip to main content

OpenAI’s o3 AI Model Falls Short of Benchmark Claims in FrontierMath Test | Technology News

OpenAI’s o3 AI Model Falls Short of Benchmark Claims in FrontierMath Test OpenAI’s o3 artificial intelligence (AI) model, which was released last week, is underperforming on a specific benchmark. Epoch AI, the company behind the FrontierMath benchmark, highlighted that the publicly available version of the o3 AI model scored 10 percent on the test, a much lower value than the company’s claim at launch.

Labels:

Comments

Post a Comment

Popular posts from this blog

Amazon Summer Sale 2022 Ends May 8: Best Deals, Offers on Phones, Smart TVs, Laptops Before Sale Ends | Technology News

Amazon Summer Sale 2022 Ends May 8: Best Deals, Offers on Phones, Smart TVs, Laptops Before Sale Ends Amazon Summer Sale 2022 will end on May 8, and customers have two more days to avail of discounts on various products during the ongoing sale. These include lowered prices on smartphones, smart TVs, and laptops. Amazon is also offering exchange discounts along with bank discounts on several products, further lowering the price. Here are some of the best deals you can ...
Post a Comment
Read more

OpenAI Releases Two Open-Source AI Models That Performs on Par With o3, o3-Mini | Technology News

OpenAI Releases Two Open-Source AI Models That Performs on Par With o3, o3-Mini OpenAI released two open-source artificial intelligence (AI) models on Tuesday. This marks the San Francisco-based AI firm’s first contribution to the open community since 2019, when GPT-2 was released in open-source. The two new models, dubbed gpt-oss-120b and gpt-oss-20b, are said to offer comparable performance as the o3 and o3-mini models.
Post a Comment
Read more