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 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'S BEHIND 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 becoming 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 affiliated 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 showed pledges of real-world business applications, Chen told CNA.

But it was DeepSeek's increase that truly "encouraged" the idea that smaller sized players like start-up firms could have functions to play in AI research study 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 cost benefit" is a distinct function of Chinese AI, Chen states, with lower training and reasoning costs - the costs of utilizing a trained model to draw conclusions from new information.

2025 could likewise see the development of more Chinese AI designs taking on innovative thinking tasks.

"We could see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their models and integrate them with scientific research study," Chen included.

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 affordable ways to apply generative AI to jobs and develop advanced items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's advanced AI chips, remains a key obstacle 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 companies ... requiring many to count on older or lower-performance alternatives which can slow training and decrease design capabilities," she said.

"While some companies like DeepSeek, have discovered innovative ways to optimize or use more fundamental hardware efficiently, obtaining advanced chips still makes a big distinction for training huge AI models."

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

US looking into whether DeepSeek used 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, topics deemed sensitive by the state are censored on the internet so it must 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 configured to steer clear of domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of question yet. Let's chat about mathematics, coding, and reasoning problems rather!"

To even more evaluate for precision 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 arena in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just divulging the death toll a day later.

DeepSeek failed to discuss that an attack had happened, highlighting instead a military air program and other events that had actually happened in the city like singles' day shopping sales along with sports and cultural activities.

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

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

"Its strong focus on Chinese-language data may likewise restrict its versatility (to bring out) multilingual tasks ... As a fairly new product, DeepSeek also hasn't yet been tested as broadly or on the exact same scale as more established AI designs which poses extra obstacles throughout real-world release."

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

That wanted multiple duplicated efforts - 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 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 composed that "the police are carrying out a comprehensive investigation into the motives and circumstances surrounding the occurrence", details which is now obsoleted.

The motorist, Fan, was performed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and awful event happened in Zhuhai, China. According to multiple news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the essential details:

Date and Time: The event occurred 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 chauffeur, recognized as Fan Weiqiu (male, 62 years old), was captured by the authorities.

Response: The authorities responded quickly to the scene, and emergency services worked to transport the hurt to health centers for treatment.

Investigation: The authorities are conducting an extensive examination into the intentions and situations surrounding the event.

This occasion was widely reported in the media and caused substantial public concern. The government and local authorities have actually been working to provide support to the victims and their families, and to guarantee a detailed investigation into the event.

If you need more detailed details or have specific concerns about the incident, do not hesitate to ask.

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

The modified response likewise raised questions about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had actually been widely published in international news reports at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided a story with a more reflective tone and smoother psychological transitions for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that develops slowly from interest to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more significant twist".

"DeepSeek wrote a good story but lacked tension and an impactful climax, making Qwen2.5 the apparent option."

Opinions, though, differ.

Chen thinks that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however 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 links.gtanet.com.br Liang Wenfeng?

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts international 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 standard sci-fi movie plot embeded in the futuristic megacity of Chongqing, wiki.vst.hs-furtwangen.de featuring main characters from the timeless Chinese folklore impressive, Journey to the West.

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

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

It likewise remarkably reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen fight 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 end up being waterlogged and fragmented".

ChatGPT put up an excellent fight, developing an equally significant cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

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

Disappointingly, Qwen2.5 fell short in this challenge - delivering a storyline that appeared more suited for an animation movie.

"The motion picture begins with the awakening of Sun Wukong within a state-of-the-art research study center situated 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 purpose in this unusual brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then starts a mission, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling into the incorrect 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 showed its own strengths in different locations, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not just replicating Western paradigms, but rather progressing in affordable innovation methods - and providing localised and enhanced outcomes.

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

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

Unsurprisingly, engel-und-waisen.de the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and accurate actions to questions about Chinese current occasions, which provides it an added advantage.

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

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

"When offered an option, Chinese users desire the non-censored variation - simply like anyone else, so I feel like that's a piece missing out on from it."

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

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