Thursday, 24 April 2025
26.8 C
Singapore
29.9 C
Thailand
19.5 C
Indonesia
28.8 C
Philippines

Did xAI mislead the public about Grok 3’s benchmarks?

xAI is under scrutiny for allegedly misleading AI benchmark results, with OpenAI employees questioning its claims about Grok 3’s performance.

Debates over AI performance benchmarks—and how they are presented—have sparked controversy in the tech world.

xAI accused of misrepresenting Grok 3’s performance

An OpenAI employee has accused Elon Musk’s AI company, xAI, of publishing misleading benchmark results for its latest AI model, Grok 3. Igor Babushkin, a co-founder of xAI, has strongly defended the company’s claims, insisting that the data was reported accurately. However, as is often the case with AI benchmarks, the truth appears more complex.

The controversy centres around a post on xAI’s blog, where the company shared a graph displaying Grok 3’s performance on AIME 2025. This benchmark consists of difficult maths questions from a recent invitational mathematics exam. While some experts question AIME’s suitability as a true measure of AI ability, it is still widely used to assess AI models’ maths skills.

In the graph, xAI claimed that two versions of Grok 3—Grok 3 Reasoning Beta and Grok 3 mini Reasoning—outperformed OpenAI’s best available model, o3-mini-high, on AIME 2025. However, OpenAI employees quickly pointed out that xAI failed to include an important detail: o3-mini-high’s score at “cons@64.”

The missing metric: What is cons@64?

The term “cons@64” stands for “consensus@64.” This means an AI model is given 64 chances to answer each problem, and its most frequently chosen answers are considered final. This method can significantly improve a model’s benchmark scores, making it a crucial factor in evaluating AI performance. Omitting this detail in a comparison graph can create a misleading impression that one model is superior when that may not be the case.

When looking at AIME 2025 results at “@1” (which only considers the model’s first attempt at answering a question), both Grok 3 Reasoning Beta and Grok 3 mini Reasoning scored lower than OpenAI’s o3-mini-high. Grok 3 Reasoning Beta also slightly underperformed compared to OpenAI’s o1 model running at a “medium” computing setting. However, xAI has marketed Grok 3 as the “world’s smartest AI.”

The broader issue of AI benchmarks

In response to the criticism, Babushkin argued on X (formerly Twitter) that OpenAI has also presented benchmark results in ways that could be considered misleading. However, OpenAI’s past comparisons mainly involved its models rather than direct competition with other companies.

An independent AI researcher compiled a more comprehensive chart showing nearly every model’s performance at cons@64 to provide a clearer picture. This chart provided a more accurate comparison but highlighted another issue: the computational cost behind these results.

As AI researcher Nathan Lambert pointed out, one of the most critical factors remains unknown—the amount of computing power and money required for each model to achieve its highest score. This raises a larger concern about AI benchmarks in general. While they can provide useful insights, they often fail to fully capture a model’s true strengths and weaknesses, leaving room for misinterpretation.

Hot this week

Razer quietly resumes laptop sales after a sudden pause in the US

Razer resumes some US laptop sales after a sudden halt, with limited models available and no explanation from the company.

xAI’s Grok chatbot now lets you ask questions about what you see

Grok’s new Vision tool lets iPhone users ask questions about what they see. Updates also add real-time voice search and memory features.

GITEX ASIA x Ai Everything Singapore unites global tech investment elite with Southeast Asia VC funding set to surpass US$13 billion in 2025

GITEX ASIA x Ai Everything Singapore brings global startups, investors, and AI innovation to the heart of Southeast Asia’s thriving tech scene.

GitLab announces general availability of GitLab Duo with Amazon Q

GitLab announces the general availability of GitLab Duo with Amazon Q, combining DevSecOps and AI to accelerate secure software development.

YouTrip adds a Malaysian Ringgit wallet to help you save more on JB trips

YouTrip now lets you store MYR and offers free JB shuttles and cashback to celebrate, making your trips across the Causeway more rewarding.

POCO launches entry-level C71 smartphone in Singapore with premium features

POCO launches the budget-friendly C71 smartphone in Singapore, offering premium design, enhanced cameras, and smooth performance at S$109.

NVIDIA uses AI to address climate, wildlife and disaster risks

NVIDIA’s AI tools support climate action, wildlife monitoring, and disaster risk mitigation, with uses spanning sea, land, sky and space.

Netflix raises subscription prices in Singapore again

Netflix again raises subscription prices in Singapore, with new rates for all plans and extra member slots.

GameMax unveils Blade Concept ATX case with bold design and powerful features

GameMax launches the Blade Concept ATX case, which features a striking blade design, RGB lighting, and support for high-end liquid-cooled PC builds.

Related Articles

Popular Categories