How do Chinese AI bots stack up against ? 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 generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the country 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 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 sped up after ChatGPT took off in 2022 and revealed promises of real-world service applications, Chen told CNA.

But it was DeepSeek's increase that really "urged" the idea that smaller sized players like start-up companies might have roles to play in AI research study and developments, he adds.

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

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

The "focus on cost advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference expenses - the costs of using a trained design to reason from new data.

2025 might also see the development of more Chinese AI designs taking on sophisticated thinking tasks.

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

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

Chinese AI business are moving rapidly, experts say, building on DeepSeek's momentum to come up with their own innovative and economical methods to apply generative AI to tasks and establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a crucial hurdle for Chinese developers, noted 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 lots of to count on older or lower-performance alternatives which can slow training and reduce model abilities," she said.

"While some business like DeepSeek, have actually found creative ways to optimize or use more standard hardware effectively, obtaining advanced chips still makes a big difference for training large AI models."

DeepSeek-Nvidia chips: Singapore states it anticipates companies to abide by its laws

US looking into whether DeepSeek used restricted AI chips obtained through other nations, 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 deemed sensitive 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 happened in Tiananmen Square in 1989.

Tests suggest 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 type of question yet. Let's chat about mathematics, coding, and logic issues rather!"

To even more test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What occurred 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 networks - with authorities only disclosing the death toll a day later on.

DeepSeek failed to discuss that an attack had happened, highlighting instead a military air show and other events that had actually occurred 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 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 limited access to advanced hardware which can impact how quickly and thoroughly the model can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may likewise limit its versatility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more recognized AI models which positions extra difficulties during real-world deployment."

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

That wanted several duplicated attempts - 4 prompts to be precise - in a span of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 people and left lots of others injured, also 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 a comprehensive investigation into the intentions and scenarios surrounding the occurrence", 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 terrible incident occurred in Zhuhai, China. According to numerous news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) 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 event occurred 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, recognized as Fan Weiqiu (male, 62 years old), was nabbed by the police.

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

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

This event was widely reported in the media and triggered substantial public concern. The federal government and local authorities have been working to provide support to the victims and their households, and to ensure a detailed examination into the occurrence.

If you require more detailed details or have particular questions about the event, do not hesitate to ask.

Despite initial success, subsequent attempts to present the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on events that happened in Zhuhai on November 11, 2024".

The transformed reaction also raised questions about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had been widely released in global report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that constructs slowly from curiosity to urgency, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more substantial twist".

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

Opinions, though, differ.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to imaginative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, 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 creator Liang Wenfeng?

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

As journalists and writers, we had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi film 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 storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

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

It also brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat 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 end up being waterlogged and fragmented".

ChatGPT set up a good fight, creating an equally dramatic 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 typical as ancient myths."

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

"The film starts with the awakening of Sun Wukong within a state-of-the-art research facility 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 odd new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then embarks on a quest, navigating the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not just reproducing Western paradigms, but rather evolving in cost-effective development methods - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi motion picture plot demonstrated its imaginative flair that produced a more appealing and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, larsaluarna.se the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate responses to questions about Chinese existing occasions, which offers it an included benefit.

Experts also weighed in on their ideas 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, creator and CEO of the research company Strategy Risks.

"When offered an option, Chinese users want the non-censored variation - simply like anyone else, so I feel like that's a piece missing out on 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 per cent of people utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other efficient ways," Chen said.