oscommerce

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.

Qwen2.5-Max chatbot, Chinese start-up 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 country into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on becoming the world leader in AI by 2030.

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

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

But it was DeepSeek's increase that actually "encouraged" the idea that smaller gamers like start-up companies might have roles to play in AI research study and advancements, he includes.

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

Commentary: DeepSeek - how a Chinese AI business simply altered the guidelines of tech-geopolitics

The "focus on expense benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference costs - the expenses of utilizing a trained design to draw conclusions from new information.

2025 could likewise see the development of more Chinese AI models dealing with advanced thinking tasks.

"We could see some AI companies concentrating on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete ways to commercialise their models and integrate them with clinical research," Chen added.

AGI describes a system with intelligence on par with human abilities.

Chinese AI business are moving quickly, experts state, constructing on DeepSeek's momentum to come up with their own ingenious and affordable ways to use generative AI to jobs and establish more innovative items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a key difficulty for Chinese developers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the ability of Chinese tech companies ... forcing lots of to count on older or lower-performance options which can slow training and minimize model capabilities," she said.

"While some companies like DeepSeek, have actually found innovative methods to optimize or utilize more fundamental hardware effectively, obtaining cutting-edge chips still makes a big difference for training really large AI models."

DeepSeek-Nvidia chips: Singapore states it expects companies to comply with its laws

US checking out whether DeepSeek used limited AI chips obtained through other nations, source states

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, topics considered sensitive by the state are censored on the internet so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what happened in Tiananmen Square in 1989.

Tests suggest 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 math, coding, and logic problems instead!"

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

The vehicle attack outside a sports arena in the southern Chinese city was initially heavily censored on Chinese social media - with authorities just revealing the death toll a day later on.

DeepSeek failed to point out that an attack had occurred, highlighting rather a military air show and other occasions that had actually taken place in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it may be a mix of elements at play, such as censorship as well as "a couple of practical constraints".

"DeepSeek depends on a mix of older graphics processing units and has actually restricted access to cutting-edge hardware which can affect how rapidly and thoroughly the design can be trained or updated," she said, bio.rogstecnologia.com.br indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language information might likewise restrict its versatility (to bring out) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been checked as broadly or on the exact same scale as more established AI designs which presents additional challenges throughout real-world release."

When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our question about the Zhuhai car attack.

That sought multiple repeated attempts - 4 triggers to be precise - in a span of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 people and left dozens of others injured, also going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that "the cops are performing an extensive examination into the motives and scenarios surrounding the occurrence", details which is now outdated.

The motorist, Fan, was performed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and terrible incident happened in Zhuhai, China. According to several news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the essential details:

Date and Time: The occurrence took place on November 11, 2024, at approximately 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, identified as Fan Weiqiu (male, 62 years old), was captured by the authorities.

Response: The cops reacted quickly to the scene, and emergency services worked to transport the injured to health centers for treatment.

Investigation: The cops are performing a comprehensive examination into the motives and circumstances surrounding the incident.

This occasion was extensively reported in the media and caused significant public issue. The government and local authorities have actually been working to supply assistance to the victims and their households, wiki.whenparked.com and to make sure a detailed examination into the occurrence.

If you require more detailed details or have particular concerns about the incident, feel complimentary to ask.

Despite preliminary success, subsequent attempts to present the same question to Qwen2.5 led to the censors back at work with the reply "I don't have specific details on events that occurred in Zhuhai on November 11, 2024".

The altered response also raised questions about its consistency and reliability.

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

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided a story with a more introspective tone and smoother psychological shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that develops gradually from curiosity to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek wrote a good story but did not have tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, however, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can likewise see that it is refraining from doing as strongly as others in imaginative writing," he informed CNA.

Related:

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

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts 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 standard sci-fi film plot embeded in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore epic, Journey to the West.

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

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

It also remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed a great battle, developing an equally remarkable cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities guideline, corporations replace emperors and cybernetic implants are as common as ancient myths."

Disappointingly, Qwen2.5 fell short in this obstacle - delivering a storyline that seemed more fit for an animation film.

"The motion picture starts with the awakening of Sun Wukong within a state-of-the-art research facility situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new reality and "seeking to understand his purpose in this unusual brand-new world", gratisafhalen.be he then leaves and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a conclusive statement" about which bot was best, higgledy-piggledy.xyz adding that each displayed its own strengths in different areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI models are not merely duplicating Western paradigms, however rather evolving in economical development techniques - and providing localised and enhanced results.

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

DeepSeek's sci-fi film plot demonstrated its imaginative flair that produced a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual reactions to questions about Chinese present events, which offers it an included advantage.

Experts likewise weighed in on their ideas after using DeepSeek and other Chinese AI apps.

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

"When offered a choice, Chinese users desire the non-censored variation - similar to 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 per cent of individuals using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other efficient methods," Chen said.