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 generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags 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 crucial" and its venture into the field has been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for pipewiki.org China Analysis.

Private and public financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed guarantees of real-world company applications, Chen told CNA.

But it was DeepSeek's rise that truly "encouraged" the concept that smaller sized players like start-up firms could have functions to play in AI research and developments, wiki.lafabriquedelalogistique.fr he adds.

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

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

The "focus on expense benefit" is an unique function of Chinese AI, Chen says, with lower training and reasoning costs - the costs of using a trained design to draw conclusions from new data.

2025 might also see the development of more Chinese AI designs tackling advanced thinking tasks.

"We might see some AI firms concentrating on getting closer to synthetic basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with clinical research," Chen included.

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

Chinese AI companies are moving quickly, analysts say, forum.altaycoins.com developing on DeepSeek's momentum to come up with their own innovative and cost-effective methods to apply generative AI to tasks and establish more innovative products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a crucial difficulty 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 ability of Chinese tech business ... forcing many to count on older or lower-performance options which can slow training and decrease design abilities," she said.

"While some companies like DeepSeek, have discovered innovative ways to optimize or utilize more standard hardware effectively, obtaining innovative chips still makes a huge distinction for training large AI models."

DeepSeek-Nvidia chips: Singapore says it expects business to adhere to its laws

US checking out whether DeepSeek used restricted 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 deemed sensitive by the state are censored on the web so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to stay away from 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 mathematics, coding, and reasoning problems instead!"

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

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

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

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

"DeepSeek counts on a mix of older graphics processing units and has actually limited access to advanced hardware which can impact how quickly and thoroughly the design can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data might likewise limit its versatility (to perform) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been tested as broadly or on the very same scale as more established AI models which postures extra difficulties throughout real-world implementation."

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

That wanted numerous duplicated attempts - four triggers to be accurate - in a span of around 20 minutes.

It ultimately relayed details about the attack which killed 35 people and left lots of others hurt, likewise going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it wrote that "the authorities are performing an extensive examination into the intentions and circumstances surrounding the event", details which is now dated.

The driver, Fan, was executed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and awful incident took place in Zhuhai, China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the key 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 resulted in 35 deaths and 43 injuries.

Perpetrator: The chauffeur, identified as Fan Weiqiu (male, 62 years old), was nabbed by the cops.

Response: The cops reacted quickly to the scene, and emergency situation services worked to carry the hurt to health centers for treatment.

Investigation: The police are carrying out a thorough investigation into the motives and scenarios surrounding the event.

This event was widely reported in the media and caused considerable public concern. The government and regional authorities have been working to provide support to the victims and their households, and to guarantee a detailed examination into the occurrence.

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

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

The altered reaction also raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been extensively published in worldwide report at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that builds gradually from curiosity to seriousness, keeping the reader engaged. It uses an unforeseen 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 abundant story with a more considerable twist".

"DeepSeek wrote a great story but lacked tension and an impactful climax, making Qwen2.5 the evident choice."

Opinions, though, vary.

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

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

Related:

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

'Made in China': genbecle.com Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts global AI scene

As journalists and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic 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 consisted of intricate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen battle 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 become waterlogged and fragmented".

ChatGPT installed an excellent battle, coming up with an equally significant cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".

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

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

"The film starts with the awakening of Sun Wukong within a modern research study facility located in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new truth and "seeking to understand his function in this odd brand-new world", wiki.myamens.com he then escapes and meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not merely replicating Western paradigms, however rather developing in economical innovation methods - and delivering localised and enhanced results.

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

DeepSeek's sci-fi film plot showed its imaginative flair that made for a more appealing and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, setiathome.berkeley.edu offers accurate and accurate actions to concerns about Chinese current occasions, which gives it an added benefit.

Experts likewise weighed in on their ideas after using DeepSeek and 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 firm Strategy Risks.

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

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

"Ninety percent of people using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other productive ways," Chen said.