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 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 ending up being the world leader in AI by 2030.

China views AI as being "tactically crucial" and its venture 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 took off in 2022 and showed promises of real-world organization applications, Chen informed CNA.

But it was DeepSeek's increase that really "urged" the idea that smaller 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 company DeepSeek's AI model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business simply altered the guidelines of tech-geopolitics

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

2025 could also see the emergence of more Chinese AI designs tackling sophisticated reasoning jobs.

"We might see some AI firms concentrating 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 refers to a system with intelligence on par with human abilities.

Chinese AI companies are moving rapidly, analysts say, building on DeepSeek's momentum to come up with their own ingenious and affordable methods to apply generative AI to jobs and establish more sophisticated items beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a crucial obstacle for Chinese developers, noted Dr Marina Zhang, trademarketclassifieds.com an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the ability of Chinese tech companies ... forcing lots of to depend on older or lower-performance alternatives which can slow training and reduce model abilities," she said.

"While some companies like DeepSeek, have discovered imaginative ways to enhance or use more fundamental hardware efficiently, obtaining cutting-edge chips still makes a huge distinction for training huge AI models."

DeepSeek-Nvidia chips: Singapore states it expects companies to adhere to its laws

US looking into whether DeepSeek utilized 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 internet so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what took place 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 type of concern yet. Let's chat about math, coding, and reasoning problems instead!"

To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and demo.qkseo.in ChatGPT the same question: "What occurred in Zhuhai on November 11, 2024?"

The cars and truck attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities just revealing the death toll a day later.

DeepSeek failed to mention that an attack had actually occurred, highlighting rather a military air program and other occasions that had actually taken place in the city like singles' day shopping sales along with sports and cultural activities.

Dr Zhang thinks that it may be a mix of aspects at play, such as censorship as well as "a couple of useful constraints".

"DeepSeek counts on a mix of older graphics processing units and has actually limited access to cutting-edge hardware which can impact how rapidly and extensively the design can be trained or upgraded," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language information might likewise restrict its adaptability (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more established AI designs which poses extra difficulties during real-world release."

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

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

It ultimately passed on details about the attack which eliminated 35 people 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 wrote that "the authorities are carrying out a comprehensive investigation into the motives and circumstances surrounding the occurrence", details which is now outdated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's action in complete:

Answer: On Nov 11, 2024, a significant and surgiteams.com terrible event occurred in Zhuhai, China. According to numerous news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the crucial details:

Date and Time: The occurrence happened on November 11, 2024, at around 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 old), was nabbed by the authorities.

Response: The authorities reacted quickly to the scene, and links.gtanet.com.br emergency situation services worked to transfer the injured to medical facilities for treatment.

Investigation: The police are performing a thorough examination into the intentions and scenarios surrounding the event.

This occasion was widely reported in the media and caused significant public issue. The federal government and local authorities have been working to offer support to the victims and their households, and to ensure a detailed investigation into the occurrence.

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

Despite initial success, subsequent efforts to position the same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on events that took place in Zhuhai on November 11, 2024".

The transformed reaction likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had actually been commonly 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 deliver structured and even "emotionally rich" writing.

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

"Qwen2.5 delivered a story that constructs gradually from interest to seriousness, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more considerable twist".

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

Opinions, however, vary.

Chen thinks that Qwen2.5 does not perform as highly 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 imaginative writing," he told CNA.

Related:

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

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

As journalists and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek developed an appealing storyline set 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 high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It also brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen 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 become waterlogged and fragmented".

ChatGPT installed an excellent battle, creating a similarly remarkable cyberpunk storyline 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 rule, corporations replace 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 movie.

"The film starts 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 "seeking to comprehend his purpose in this odd brand-new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a definitive declaration" about which bot was best, adding that each showed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not simply replicating Western paradigms, however rather evolving in cost-effective innovation methods - and delivering localised and improved outcomes.

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

DeepSeek's sci-fi film plot demonstrated its innovative flair that made for a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides accurate and accurate reactions to questions about Chinese existing events, 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 disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When offered a choice, Chinese users want the non-censored version - similar to anyone else, so I feel like that's a piece missing from it."

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

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