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 generated 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 "strategically important" 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 engel-und-waisen.de China Analysis.

Private and public financial investments in Chinese AI sped up after ChatGPT took off in 2022 and showed pledges of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that really "encouraged" the concept that smaller sized players like start-up companies could have functions to play in AI research study and advancements, he adds.

'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 altered the rules of tech-geopolitics

The "focus on cost advantage" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning costs - the costs of utilizing a trained design to draw conclusions from brand-new data.

2025 might also see the development of more Chinese AI models taking on advanced reasoning tasks.

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

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

Chinese AI companies are moving quickly, analysts state, developing on DeepSeek's momentum to come up with their own innovative and economical ways to use generative AI to tasks and establish more innovative products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's advanced AI chips, wiki.dulovic.tech remains an essential difficulty 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 numerous to count on older or lower-performance options which can slow training and reduce model abilities," she said.

"While some business like DeepSeek, have found imaginative ways to optimize or use more fundamental hardware effectively, obtaining advanced chips still makes a huge difference for training huge AI designs."

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

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

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, topics considered sensitive by the state are censored on the internet so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to avoid 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 math, coding, and reasoning problems rather!"

To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "What took place in Zhuhai on November 11, 2024?"

The car attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social media - with authorities only revealing the death toll a day later on.

DeepSeek failed to discuss that an attack had actually taken place, highlighting rather a military air program and wiki.myamens.com other occasions that had happened in the city like songs' day shopping sales along with sports and cultural activities.

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

"DeepSeek counts on a mix of older graphics processing units and has limited access to cutting-edge hardware which can affect how quickly and extensively the model can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data might likewise limit its flexibility (to carry out) multilingual jobs ... As a fairly new product, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more established AI models which presents extra obstacles during real-world release."

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

That was after several repeated efforts - 4 prompts to be exact - in a span of around 20 minutes.

It ultimately communicated details about the attack which eliminated 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 wrote that "the police are performing an extensive investigation into the motives and circumstances surrounding the event", details which is now dated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's action in complete:

Answer: On Nov 11, 2024, a significant and awful event happened in Zhuhai, wiki.dulovic.tech China. According to multiple news sources, archmageriseswiki.com a man called Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a substantial number of casualties. Here are the crucial details:

Date and Time: The event 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 driver, determined as Fan Weiqiu (male, 62 years old), was apprehended by the police.

Response: The cops reacted quickly to the scene, and emergency services worked to transport the injured to hospitals for treatment.

Investigation: The police are performing a thorough investigation into the motives and circumstances surrounding the event.

This occasion was widely reported in the media and triggered significant public issue. The federal government and local authorities have been working to supply support to the victims and their families, and to make sure a detailed investigation into the event.

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

Despite initial success, surgiteams.com subsequent attempts to position the same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on occasions that occurred in Zhuhai on November 11, 2024".

The altered action also raised questions about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been widely published in global news reports at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have praised the ability 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 transitions for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that develops gradually from interest to urgency, keeping the reader engaged. It offers an unexpected 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, emotionally rich story with a more significant twist".

"DeepSeek wrote an excellent story however did not have tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, differ.

Chen thinks that Qwen2.5 does not carry out as highly as DeepSeek and 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, pleasant surprise from Chinese netizens as DeepSeek shocks worldwide AI scene

As reporters and authors, we had to see this for ourselves so we put each bot to the test - to come up with a movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, Journey to the West.

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

It consisted of fancy 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 "a sarcastic, self-aware AI housed in a taken battle body", Zhu Bajie as a cyborg club owner "drowning in debt 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 an excellent battle, creating an equally remarkable cyberpunk story 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 difficulty - providing a storyline that seemed more matched for an animation movie.

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

Realising his new reality and "seeking to comprehend his purpose in this strange new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then starts a mission, navigating the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not simply duplicating Western paradigms, but rather evolving in cost-efficient innovation methods - and providing localised and enhanced results.

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

DeepSeek's sci-fi movie plot showed its creative flair that produced a more engaging and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate responses to concerns about Chinese present events, which provides it an added benefit.

Experts also weighed in on their ideas after using DeepSeek and other Chinese AI apps.

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

"When provided a choice, Chinese users want the non-censored version - 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, especially for Chinese users.

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