Discover ANY AI to make more online for less.

select between over 22,900 AI Tool and 17,900 AI News Posts.

<
New
Agents
Marketing
Video
Image
Music
Coding
Communication
Education
Travel
>

Gemini 3 Pro and GPT-5 still fail at complex physics tasks designed for real scientific research
Gemini 3 Pro and GPT-5 still fail at complex physics tasks designed for real scientific research

A new physics benchmark called "CritPt" puts leading AI models to the test at the level of early-stage PhD research. The results show that even top systems like Gemini 3 Pro and GPT-5 still fall far short of acting as autonomous scientists.
The article Gemini 3 Pro and GPT-5 still fail at complex physics tasks designed for real scientific research appeared first on THE DECODER.

Discover Copy
Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

venturebeat
Artificial Analysis overhauls its AI Intelligence Index, replacing popular

<p>The arms race to build smarter AI models has a measurement problem: the tests used to rank them are becoming obsolete almost as quickly as the models improve. On Monday, <a href="http [...]

Match Score: 138.75

venturebeat
Gemini 3 Flash arrives with reduced costs and latency — a powerful combo

<p>Enterprises can now harness the power of a large language model that&#x27;s near that of the state-of-the-art<a href="https://venturebeat.com/ai/google-unveils-gemini-3-claiming-t [...]

Match Score: 136.28

venturebeat
OpenAI is ending API access to fan-favorite GPT-4o model in February 2026

<p>OpenAI has sent out emails notifying API customers that its chatgpt-4o-latest model will be retired from the developer platform in mid-February 2026,. </p><p>Access to the model i [...]

Match Score: 136.02

venturebeat
Google unveils Gemini 3 claiming the lead in math, science, multimodal and

<p>After more than a month of rumors and feverish speculation — including <a href="https://polymarket.com/event/gemini-3pt0-released-by">Polymarket wagering on the release date [...]

Match Score: 135.27

venturebeat
Upwork study shows AI agents excel with human partners but fail independent

<p>Artificial intelligence agents powered by the world&#x27;s most advanced language models routinely fail to complete even straightforward professional tasks on their own, according to < [...]

Match Score: 120.85

venturebeat
OpenAI's GPT-5.2 is here: what enterprises need to know

<p>The rumors were true, and the &quot;<a href="https://www.theinformation.com/articles/openai-ceo-declares-code-red-combat-threats-chatgpt-delays-ads-effort">Code Red</a& [...]

Match Score: 117.66

Google's Michel Devoret is one of the 2025 winners of the Nobel Prize in Physics
Google's Michel Devoret is one of the 2025 winners of the Nobel Prize

<p>The Royal Swedish Academy of Sciences <a data-i13n="elm:context_link;elmt:doNotAffiliate;cpos:1;pos:1" class="no-affiliate-link" href="https://www.nobelprize.org/p [...]

Match Score: 85.67

venturebeat
OpenAI reboots ChatGPT experience with GPT-5.1 after mixed reviews of GPT-5

<p>ChatGPT is about to become faster and more conversational as <a href="https://openai.com/"><u>OpenAI</u></a> upgrades its <a href="https://venturebea [...]

Match Score: 84.30

venturebeat
What enterprises should know about The White House's new AI 'Manh

<p>President Donald Trump’s new “<a href="https://www.whitehouse.gov/presidential-actions/2025/11/launching-the-genesis-mission/">Genesis Mission</a>” unveiled Monday [...]

Match Score: 82.18