Storia in 4 fonti

Mathematicians grade AI performance on complex problem set at Harvard

Thirty mathematicians at Harvard blind-graded AI solutions to 10 original research-level math problems. AI passed seven but struggled with the hardest

Raccontata da

Confronto fonti

4 prospettive sulla stessa storia

AI · summaries

cryptobriefing.comStai leggendo3 g fa

Mathematicians grade AI performance on complex problem set at Harvard

Harvard mathematicians tested OpenAI and Google AI on 10 unpublished research math problems; models solved 7 of 10, versus 2-of-10 earlier. The jump signals genuine reasoning capacity beyond pattern-matching—essential intel for CTOs evaluating AI for research-grade technical work.

originale

iol.co.za2 g fa

A new era for mathematics: AI excels in grading major problem sets

A gathering of mathematicians at Harvard grades a set of AI-solved problems, revealing key insights into the strengths and weaknesses of artificial intelligence in the realm of abstract reasoning. As the debate over…

Leggi questa versione →

Timeline cronologica

venerdì 12 giugno 2026·nature.com
Humans outperform AI at this highly rigorous mathematics test
A new benchmark pitting AI against previously unseen maths problems shows systems still fall short of top human expertise.
lunedì 15 giugno 2026·cryptobriefing.com
Mathematicians grade AI performance on complex problem set at Harvard
Thirty mathematicians at Harvard blind-graded AI solutions to 10 original research-level math problems. AI passed seven but struggled with the hardest

Mathematicians grade AI performance on complex problem set at Harvard

Confronto fonti

Mathematicians grade AI performance on complex problem set at Harvard

A new era for mathematics: AI excels in grading major problem sets

Timeline cronologica

Humans outperform AI at this highly rigorous mathematics test

Mathematicians grade AI performance on complex problem set at Harvard

Humans outperform AI at this highly rigorous mathematics test

AI just took the world's hardest maths test and humans won

A new era for mathematics: AI excels in grading major problem sets

AI just took the world's hardest maths test and humans won