How do Chinese aI Bots Stack up Against ChatGPT?

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 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 produced 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 foray 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 revealed promises of real-world business applications, Chen told CNA.

But it was DeepSeek’s rise that actually “encouraged” the idea that smaller sized players like start-up firms might have roles to play in AI research and developments, 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 company just changed the guidelines of tech-geopolitics

The “focus on expense advantage” is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference costs – the costs of using a trained design to reason from new information.

2025 might likewise see the development of more Chinese AI designs tackling innovative reasoning jobs.

“We could see some AI companies focusing on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their designs and incorporate them with scientific research study,” Chen added.

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

Chinese AI companies are moving quickly, analysts state, developing on DeepSeek’s momentum to come up with their own ingenious and cost-efficient methods to use generative AI to tasks and develop advanced items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia’s sophisticated AI chips, remains an essential obstacle for Chinese designers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney’s (UTS) Institute.

“US export controls (still) limit the capability of Chinese tech companies … forcing lots of to rely on older or lower-performance options which can slow training and minimize design abilities,” she said.

“While some companies like DeepSeek, have actually discovered imaginative ways to optimize or utilize more basic hardware effectively, obtaining innovative chips still makes a huge difference for training huge AI designs.”

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

US looking into whether DeepSeek utilized restricted AI chips obtained through other nations, source states

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

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

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

Tests recommend Chinese chatbots are set to guide clear of domestic politics.

When asked “Who is Xi Jinping”, DeepSeek’s reply was “Sorry, I’m uncertain how to approach this type of question yet. Let’s chat about math, coding, and logic issues instead!”

To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: “What took place 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 only divulging the death toll a day later.

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

Dr Zhang believes that it may be a mix of elements at play, such as censorship along with “a couple of practical constraints”.

“DeepSeek depends on a mix of older graphics processing systems and has actually restricted access to advanced hardware which can affect how rapidly and thoroughly the model can be trained or upgraded,” she said, indicating existing US export curbs on China.

“Its strong concentrate on Chinese-language data may likewise restrict its adaptability (to carry out) multilingual tasks … As a fairly new item, DeepSeek also hasn’t yet been tested as broadly or on the very same scale as more recognized AI designs which presents extra obstacles throughout real-world release.”

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

That sought several duplicated efforts – four triggers to be accurate – in a span of around 20 minutes.

It ultimately passed on details about the attack which killed 35 individuals and left lots of others hurt, bytes-the-dust.com 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 an extensive examination into the intentions and scenarios surrounding the occurrence”, details which is now outdated.

The motorist, Fan, was executed last month.

This is Qwen2.5’s response completely:

Answer: On Nov 11, 2024, a major and tragic incident happened in Zhuhai, China. According to numerous news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the essential details:

Date and Time: The occurrence occurred 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 chauffeur, determined as Fan Weiqiu (male, 62 years old), was collared by the cops.

Response: The authorities reacted rapidly to the scene, and yewiki.org emergency situation services worked to carry the hurt to medical facilities for treatment.

Investigation: The cops are conducting a comprehensive investigation into the intentions and scenarios surrounding the incident.

This event was extensively reported in the media and triggered substantial public issue. The federal government and regional authorities have been working to provide assistance to the victims and their families, and to make sure a detailed investigation into the occurrence.

If you require more detailed details or have particular questions about the event, feel free to ask.

Despite preliminary success, subsequent attempts to present the very same concern to Qwen2.5 led to the censors back at work with the reply “I don’t have particular details on occasions that occurred 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 actually been commonly released in international report at the time of the accident – so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the capability of Chinese AI apps to provide structured and even “mentally abundant” writing.

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

“Qwen2.5 delivered a story that builds slowly from curiosity to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting,” she said, including that Qwen2.5 eventually “crafted a more cinematic, emotionally abundant story with a more substantial twist”.

“DeepSeek composed an excellent story however lacked tension and an impactful climax, making Qwen2.5 the obvious option.”

Opinions, though, differ.

Chen thinks 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 tasks, but we can also see that it is refraining from doing as highly as others in innovative writing,” he informed CNA.

Related:

China’s brand-new face of AI: Who is DeepSeek creator Liang Wenfeng?

‘Made in China’: Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts international AI scene

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

True to form, DeepSeek developed an interesting storyline set in the year 2145 entitled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism combines with quantum computing”.

It included intricate settings – smoggy skies “pierced by skyscrapers”, “holographic lanterns that drift above neon-lit streets” and “ancient temples nestled between quantum server farms”.

It also remarkably reimagined conventional heroes Sun Wukong as “an ironical, self-aware AI housed in a taken fight body”, Zhu Bajie as a cyborg nightclub owner “drowning in financial obligation and vices” and Sha Wujing as a “quiet hulking android” from the Yangtze River, systemcheck-wiki.de whose “memory cores end up being waterlogged and fragmented”.

ChatGPT installed an excellent fight, developing an equally remarkable cyberpunk story which similarly reimagined “a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West”.

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

Disappointingly, Qwen2.5 fell short in this difficulty – providing a story that seemed more suited for an animation movie.

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

Realising his new reality and “seeking to understand his purpose in this unusual brand-new world”, he then escapes and meets Zhu Bajie and Sha Wujing – “each battling with their own existential crises”.

The trio then starts a mission, browsing the streets of Chongqing to safeguard the sacred “Eternal Scroll” from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was “tough to make a definitive declaration” about which bot was best, adding that each showed its own strengths in various locations, “such as language focus, training data and hardware optimization”.

Her insight underscores how Chinese AI designs are not merely reproducing Western paradigms, however rather progressing in cost-effective 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 creative flair that made for a more appealing and imaginative narrative as compared to Qwen2.5 and ChatGPT’s efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and accurate actions to concerns about Chinese current occasions, which provides it an included benefit.

Experts also weighed in on their thoughts 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 study firm Strategy Risks.

“When given a choice, Chinese users desire the non-censored version – much like anybody else, so I seem like that’s a piece missing 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 productive ways,” Chen said.