Morning Overview on MSN

General AI now performs at or above human-expert level on standardized tests in many fields

Large language models built by Google, OpenAI, and academic research teams have matched or exceeded human-expert scores on ...
ZDNet

With AI models clobbering every benchmark, it's time for human evaluation

Artificial intelligence has traditionally advanced through automatic accuracy tests in tasks meant to approximate human knowledge. Carefully crafted benchmark tests such as The General Language ...
Morning Overview on MSN

AI systems now match or beat human experts across a widening range of professional and scientific exams, Stanford’s 2026 index finds

Frontier AI models now match or surpass human expert performance on graduate-level science exams, competition mathematics, ...
Gizmodo

OpenAI Claims Its New Model Reached Human Level on a Test for ‘General Intelligence.’ What Does That Mean?

OpenAI’s o3 system scored 85% on the ARC-AGI benchmark, well above the previous AI best score of 55% and on par with the average human score. Reading time 4 minutes A new artificial intelligence (AI) ...
TMCnet

Lockton and Nexar Introduce Human-Benchmark Framework for Autonomous Vehicle Safety

Lockton, the world's largest privately held insurance brokerage, and Nexar, the real-world intelligence platform for the Physical AI era, today introduced a human-benchmark framework for evaluating ...
UPI

AI model achieves human level performance on general intelligence test

Dec. 24 (UPI) --A new artificial intelligence (AI) model has just achieved human-level results on a test designed to measure "general intelligence". On December 20, OpenAI's o3 system scored 85% on ...
Time

AI Models Are Getting Smarter. New Tests Are Racing to Catch Up

Follow this section to personalize your feed and get instant alerts. WHY FOLLOW? Update your preferences in Account Settings Personalized Content Follow this tag to personalize your feed and get ...
MIT Technology Review

AI benchmarks are broken. Here’s what we need instead.

One-off tests don’t measure AI’s true impact. We’re better off shifting to more human-centered, context-specific methods. For decades, artificial intelligence has been evaluated through the question ...
The Conversation

An AI system has reached human level on a test for ‘general intelligence’. Here’s what that means

A new artificial intelligence (AI) model has just achieved human-level results on a test designed to measure “general intelligence”. On December 20, OpenAI’s o3 system scored 85% on the ARC-AGI ...