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 start-up DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

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

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

Private and public financial investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed promises of real-world organization applications, Chen told CNA.

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

'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 company just changed the guidelines of tech-geopolitics

The "emphasis on cost advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and raovatonline.org reasoning costs - the costs of using a trained model to reason from new information.

2025 might also see the development of more Chinese AI models tackling innovative thinking jobs.

"We might see some AI companies focusing on getting closer to artificial general intelligence (AGI) while others focus on concrete methods to commercialise their designs and integrate them with clinical research," Chen added.

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

Chinese AI business are moving rapidly, experts state, it-viking.ch constructing on DeepSeek's momentum to come up with their own innovative and economical methods to apply generative AI to tasks and establish advanced items beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's advanced AI chips, remains an essential hurdle for Chinese designers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the ability of Chinese tech business ... forcing numerous to depend on older or lower-performance options which can slow training and lower model capabilities," she said.

"While some business like DeepSeek, have actually found imaginative ways to optimize or utilize more standard hardware effectively, obtaining cutting-edge chips still makes a big difference for training large AI models."

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

US looking into whether DeepSeek used 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 web 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 suggest Chinese chatbots are set to steer 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 mathematics, coding, and reasoning problems rather!"

To even more test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact 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 revealing the death toll a day later.

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

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

"DeepSeek depends on a mix of older graphics processing systems and has limited access to innovative hardware which can affect how rapidly and thoroughly the design can be trained or upgraded," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language data might also restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the exact same scale as more established AI models which postures additional obstacles throughout real-world deployment."

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

That sought multiple duplicated attempts - four triggers to be exact - in a period of around 20 minutes.

It eventually communicated details about the attack which killed 35 individuals and wiki.myamens.com left dozens of others injured, 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 authorities are conducting an extensive examination into the intentions and scenarios surrounding the occurrence", details which is now obsoleted.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and terrible incident occurred in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a significant 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, determined as Fan Weiqiu (male, 62 years old), was nabbed by the cops.

Response: The cops responded rapidly to the scene, and emergency services worked to transfer the injured to hospitals for treatment.

Investigation: The authorities are performing a thorough examination into the intentions and scenarios surrounding the incident.

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

If you need more detailed details or have specific questions about the occurrence, feel free to ask.

Despite preliminary success, subsequent efforts to posture the exact 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 modified action also raised questions about its consistency and reliability.

Predictably, ChatGPT cited 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 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 provided a story that constructs gradually from curiosity to urgency, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek wrote an excellent story but lacked tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, though, vary.

Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and yewiki.org 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 strongly as others in imaginative writing," he informed CNA.

Related:

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

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

As reporters and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, Journey to the West.

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

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

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

ChatGPT installed a great battle, coming up with an equally remarkable cyberpunk story 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 guideline, corporations change emperors and cybernetic implants are as common as ancient misconceptions."

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

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

Realising his new reality and "seeking to understand his function in this strange brand-new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under 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 information and hardware optimization".

Her insight highlights how Chinese AI designs are not merely reproducing Western paradigms, however rather progressing in cost-efficient innovation techniques - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi film plot demonstrated its creative 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 precise and factual responses to questions about Chinese existing events, which gives it an added advantage.

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

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

"When given an option, Chinese users want the non-censored variation - much like anyone else, so I seem like that's a piece missing from it."

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

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