
arstechnica.com/ai/2025/04/new-study-shows-why-simulated-reasoning-ai-models-dont-yet-live-up-to-their-billing
Preview meta tags from the arstechnica.com website.
Linked Hostnames
20- 48 links toarstechnica.com
- 3 links toartofproblemsolving.com
- 3 links toarxiv.org
- 3 links towww.condenast.com
- 2 links toen.wikipedia.org
- 1 link tobsky.app
- 1 link tocdn.arstechnica.net
- 1 link togarymarcus.substack.com
Thumbnail

Search Engine Appearance
https://arstechnica.com/ai/2025/04/new-study-shows-why-simulated-reasoning-ai-models-dont-yet-live-up-to-their-billing
New study shows why simulated reasoning AI models don’t yet live up to their billing
Top AI models excel at math problems but lack reasoning needed for Math Olympiad proofs.
Bing
New study shows why simulated reasoning AI models don’t yet live up to their billing
https://arstechnica.com/ai/2025/04/new-study-shows-why-simulated-reasoning-ai-models-dont-yet-live-up-to-their-billing
Top AI models excel at math problems but lack reasoning needed for Math Olympiad proofs.
DuckDuckGo

New study shows why simulated reasoning AI models don’t yet live up to their billing
Top AI models excel at math problems but lack reasoning needed for Math Olympiad proofs.
General Meta Tags
13- titleNew study shows why simulated reasoning AI models don’t yet live up to their billing - Ars Technica
- charsetutf-8
- viewportwidth=device-width, initial-scale=1
- robotsmax-snippet:-1,max-image-preview:large,max-video-preview:-1
- descriptionTop AI models excel at math problems but lack reasoning needed for Math Olympiad proofs.
Open Graph Meta Tags
10- og:typearticle
og:locale
en_US- og:site_nameArs Technica
- og:titleNew study shows why simulated reasoning AI models don’t yet live up to their billing
- og:descriptionTop AI models excel at math problems but lack reasoning needed for Math Olympiad proofs.
Twitter Meta Tags
8- twitter:cardsummary_large_image
- twitter:titleNew study shows why simulated reasoning AI models don’t yet live up to their billing
- twitter:descriptionTop AI models excel at math problems but lack reasoning needed for Math Olympiad proofs.
- twitter:imagehttps://cdn.arstechnica.net/wp-content/uploads/2025/04/math_question_1-1152x648.jpg
- twitter:image:altIllustration of a robot standing on a latter in front of a large chalkboard solving mathematical problems. A red question mark hovers over its head.
Link Tags
13- apple-touch-iconhttps://cdn.arstechnica.net/wp-content/uploads/2016/10/cropped-ars-logo-512_480-300x300.png
- canonicalhttps://arstechnica.com/ai/2025/04/new-study-shows-why-simulated-reasoning-ai-models-dont-yet-live-up-to-their-billing/
- iconhttps://cdn.arstechnica.net/wp-content/uploads/2016/10/cropped-ars-logo-512_480-60x60.png
- iconhttps://cdn.arstechnica.net/wp-content/uploads/2016/10/cropped-ars-logo-512_480-300x300.png
- preconnecthttps://c.arstechnica.com
Emails
1Links
74- https://arstechnica.com
- https://arstechnica.com/about-us
- https://arstechnica.com/affiliate-link-policy
- https://arstechnica.com/ai
- https://arstechnica.com/ai/2024/01/deepmind-ai-rivals-the-worlds-smartest-high-schoolers-at-geometry