ai-robotics

How do Chinese AI bots stack up against ChatGPT? We put them to the test

The heat is on as China's tech giants step up their video game after DeepSeek's success.

Alibaba's Qwen2.5-Max chatbot, Chinese startup DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has long been President Xi Jinping's objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "tactically crucial" and its foray into the field has been "years in the making", said Chen Qiheng, an affiliated scientist at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT removed in 2022 and showed pledges of real-world business applications, Chen told CNA.

But it was DeepSeek's increase that really "urged" the concept that smaller players like start-up companies might have roles to play in AI research study and developments, he includes.

'A lot is up in the air': Is Chinese firm DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business just changed the rules of tech-geopolitics

The "focus on cost advantage" is a distinctive feature of Chinese AI, Chen says, with lower training and reasoning costs - the expenses of using a trained design to draw conclusions from new data.

2025 could also see the development of more Chinese AI designs dealing with sophisticated reasoning jobs.

"We could see some AI firms concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and incorporate them with scientific research," Chen added.

AGI refers to a system with intelligence on par with human abilities.

Chinese AI companies are moving quickly, experts state, building on DeepSeek's momentum to come up with their own innovative and cost-effective ways to use generative AI to tasks and develop advanced products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a crucial obstacle for Chinese developers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the capability of Chinese tech companies ... forcing many to rely on older or lower-performance options which can slow training and decrease design capabilities," she said.

"While some business like DeepSeek, have actually discovered creative methods to enhance or use more fundamental hardware efficiently, obtaining innovative chips still makes a huge distinction for training large AI models."

DeepSeek-Nvidia chips: Singapore states it expects companies to abide by its laws

US checking out whether DeepSeek utilized limited AI chips obtained through other nations, source says

So how do Chinese AI bots match up against ChatGPT? We put them to the test.

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, subjects considered delicate by the state are censored on the internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to stay away from domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about mathematics, coding, and logic problems instead!"

To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What occurred in Zhuhai on November 11, 2024?"

The cars and truck attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities just divulging the death toll a day later.

DeepSeek failed to mention that an attack had actually occurred, highlighting instead a military air program and other occasions that had happened in the city like singles' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it may be a mix of elements at play, such as censorship in addition to "a few useful constraints".

"DeepSeek relies on a mix of older graphics processing systems and has restricted access to advanced hardware which can affect how quickly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language information may likewise limit its versatility (to carry out) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the exact same scale as more established AI models which postures extra obstacles during real-world deployment."

When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai cars and truck attack.

That sought several repeated attempts - four triggers to be exact - in a span of around 20 minutes.

It ultimately passed on details about the attack which killed 35 individuals and left dozens of others hurt, likewise going on to note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it wrote that "the police are conducting a comprehensive examination into the motives and scenarios surrounding the incident", details which is now obsoleted.

The driver, Fan, was executed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and terrible event took place in Zhuhai, China. According to several news sources, a male named Fan Weiqiu (樊某, raovatonline.org male, 62 years old) drove a cars and ratemywifey.com truck into a crowd at the Zhuhai Sports Center, resulting in a considerable number of casualties. Here are the key details:

Date and Time: The incident happened on November 11, 2024, at roughly 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The attack led to 35 deaths and 43 injuries.

Perpetrator: The driver, recognized as Fan Weiqiu (male, 62 years old), was collared by the cops.

Response: The police responded rapidly to the scene, and emergency situation worked to carry the hurt to healthcare facilities for treatment.

Investigation: The police are performing an extensive investigation into the motives and circumstances surrounding the event.

This event was extensively reported in the media and caused considerable public issue. The federal government and regional authorities have been working to offer assistance to the victims and their households, and to guarantee a detailed examination into the event.

If you require more detailed details or have specific questions about the incident, feel totally free to ask.

Despite initial success, subsequent attempts to position the exact same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on events that happened in Zhuhai on November 11, 2024".

The altered reaction likewise raised questions about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had been extensively published in international news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the ability of Chinese AI apps to provide structured and even "emotionally abundant" writing.

"DeepSeek-R1 offered a story with a more reflective tone and smoother emotional transitions for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that builds slowly from curiosity to urgency, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more substantial twist".

"DeepSeek composed a great story but did not have tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, though, vary.

Chen thinks that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as highly as others in creative writing," he told CNA.

Related:

China's new face of AI: Who is DeepSeek creator Liang Wenfeng?

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks international AI scene

As journalists and writers, we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore impressive, Journey to the West.

True to form, DeepSeek came up with an engaging story embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It included sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg bar owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT set up a great battle, creating a similarly significant cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

"This is a world where AI deities guideline, corporations change emperors and cybernetic implants are as typical as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this obstacle - providing a storyline that appeared more suited for an animation film.

"The film begins with the awakening of Sun Wukong within a high-tech research center situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new truth and "looking for to understand his purpose in this strange new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then embarks on a quest, navigating the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "difficult to make a conclusive statement" about which bot was best, garagesale.es including that each showed its own strengths in different locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not simply reproducing Western paradigms, however rather evolving in cost-efficient development methods - and delivering localised and enhanced results.

In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.

DeepSeek's sci-fi film plot showed its innovative flair that produced a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual actions to questions about Chinese existing occasions, which offers it an included advantage.

Experts also weighed in on their thoughts after using DeepSeek and wiki.snooze-hotelsoftware.de other Chinese AI apps.

"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research study company Strategy Risks.

"When provided an option, Chinese users desire the non-censored variation - simply like anybody else, so I feel like that's a piece missing out on from it."

Independent Beijing-based specialist Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly for Chinese users.

"Ninety percent of individuals utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other efficient ways," Chen said.