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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the country into a tech superpower has 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 foray into the field has actually been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for China Analysis.

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

But it was DeepSeek's rise that truly "encouraged" the concept that smaller gamers like start-up firms might have functions to play in AI research study and advancements, he adds.

'A lot is up in the air': wiki.dulovic.tech Is Chinese company DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI company just altered the rules of tech-geopolitics

The "focus on cost benefit" is an unique function of Chinese AI, Chen states, with lower training and inference expenses - the costs of utilizing a trained model to draw conclusions from brand-new information.

2025 might also see the development of more Chinese AI models taking on sophisticated thinking jobs.

"We could see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete methods to commercialise their models and integrate them with clinical research study," Chen included.

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

Chinese AI companies are moving rapidly, analysts say, developing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative AI to tasks and develop more advanced items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's innovative AI chips, remains a key hurdle for Chinese designers, kept in mind Dr Marina Zhang, an associate teacher 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 rely on older or lower-performance alternatives which can slow training and reduce model capabilities," she said.

"While some business like DeepSeek, have found creative ways to enhance or utilize more basic hardware efficiently, obtaining advanced chips still makes a big distinction for training large AI designs."

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

US checking out whether DeepSeek utilized restricted AI chips obtained through other countries, source says

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 web so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured 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 issues instead!"

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

The vehicle attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social media - with authorities only disclosing the death toll a day later.

DeepSeek failed to point out that an attack had actually happened, highlighting instead a military air program and higgledy-piggledy.xyz other events that had taken place in the city like singles' day shopping sales in addition to sports and cultural activities.

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

"DeepSeek counts on a mix of older graphics processing systems and has limited access to innovative hardware which can impact how quickly and thoroughly the model can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language data might likewise limit its versatility (to perform) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been tested as broadly or on the very same scale as more recognized AI models which postures additional challenges during real-world release."

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

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

It eventually communicated details about the attack which killed 35 individuals and left lots of others injured, also going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the police are performing a comprehensive investigation into the motives and scenarios surrounding the occurrence", yewiki.org details which is now dated.

The motorist, Fan, was executed last month.

This is Qwen2.5's reaction in complete:

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

Date and Time: The incident 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, recognized as Fan Weiqiu (male, 62 years of ages), was apprehended by the police.

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

Investigation: The authorities are conducting a thorough examination into the intentions and situations surrounding the occurrence.

This occasion was widely reported in the media and caused significant public concern. The government and local authorities have been working to offer support to the victims and their families, and to guarantee a detailed examination into the incident.

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

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

The modified response also raised concerns about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been extensively published in international report at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 offered 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 seriousness, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more substantial twist".

"DeepSeek composed a good story however did not have stress and an impactful climax, making Qwen2.5 the evident choice."

Opinions, however, differ.

Chen thinks that Qwen2.5 does not perform as highly 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 highly as others in creative writing," he informed CNA.

Related:

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

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

As journalists and authors, we had to see this for wiki.myamens.com ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore legendary, Journey to the West.

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

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

It likewise brilliantly reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a taken battle body", Zhu Bajie as a cyborg club owner "drowning in financial obligation and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up a great fight, coming up with a similarly remarkable cyberpunk storyline 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 rule, corporations change emperors and cybernetic implants are as common as ancient misconceptions."

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

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

Realising his brand-new truth and "looking for to comprehend his function 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 embarks on a mission, navigating 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 "hard to make a conclusive declaration" about which bot was best, adding that each displayed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not merely reproducing Western paradigms, but rather evolving in cost-effective development methods - and providing localised and improved results.

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

DeepSeek's sci-fi film plot showed its creative flair that made for a more appealing and links.gtanet.com.br creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, fishtanklive.wiki the more recognized ChatGPT, wiki.vst.hs-furtwangen.de unburdened by Chinese censorship constraints, provides accurate and factual actions to questions about Chinese present occasions, which gives it an added advantage.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.

"When offered an option, Chinese users want the non-censored version - just like anybody 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, particularly for Chinese users.

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