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'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 "tactically essential" and its venture into the field has actually been "years in the making", said Chen Qiheng, an affiliated scientist 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 promises of real-world organization applications, Chen told CNA.

But it was DeepSeek's increase that actually "urged" the concept 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 company DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business simply changed the rules of tech-geopolitics

The "emphasis on cost advantage" is a distinctive feature of Chinese AI, Chen says, with lower training and inference expenses - the costs of utilizing a trained model to reason from brand-new information.

2025 might also see the emergence of more Chinese AI designs taking on innovative reasoning tasks.

"We could see some AI firms concentrating on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and incorporate them with clinical research," Chen added.

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

Chinese AI business are moving rapidly, analysts say, constructing on DeepSeek's momentum to come up with their own ingenious and economical ways to use generative AI to tasks and establish advanced products beyond chatbots.

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

"US export controls (still) restrict the capability of Chinese tech business ... requiring lots of to depend on older or lower-performance alternatives which can slow training and minimize design abilities," she said.

"While some companies like DeepSeek, have found innovative methods to enhance or use more basic hardware effectively, obtaining cutting-edge chips still makes a big difference for training huge AI models."

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

US looking into whether DeepSeek used restricted AI chips obtained through other countries, source states

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 delicate by the state are censored on the web so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to stay away from domestic politics.

When asked "Who is Xi Jinping", it-viking.ch DeepSeek's reply was "Sorry, I'm uncertain how to approach this type of concern yet. Let's chat about math, coding, and logic problems instead!"

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

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

DeepSeek failed to point out that an attack had actually happened, highlighting rather a military air program and other events that had happened in the city like songs' day shopping sales along with sports and wiki.snooze-hotelsoftware.de cultural activities.

Dr Zhang thinks that it might be a mix of at play, such as censorship along with "a few practical constraints".

"DeepSeek relies on a mix of older graphics processing systems and has actually limited access to advanced hardware which can affect how quickly and extensively the design can be trained or upgraded," she said, pointing to existing US export curbs on China.

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

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

That was after multiple repeated attempts - 4 triggers to be accurate - in a period of around 20 minutes.

It eventually relayed details about the attack which eliminated 35 people and left dozens of others injured, likewise going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it composed that "the police are conducting a thorough examination into the intentions and situations surrounding the occurrence", details which is now outdated.

The motorist, Fan, was performed last month.

This is Qwen2.5's response in complete:

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

Date and Time: The occurrence happened 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, identified as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

Response: The police reacted quickly to the scene, and emergency situation services worked to transport the injured to health centers for treatment.

Investigation: The cops are performing a comprehensive investigation into the motives and scenarios surrounding the event.

This event was commonly reported in the media and caused substantial public concern. The federal government and regional authorities have actually been working to provide support to the victims and their families, and to ensure a detailed examination into the incident.

If you need more detailed details or have particular questions about the occurrence, feel free to ask.

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

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

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

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 used 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 constructs gradually from interest to seriousness, keeping the reader engaged. It provides an unanticipated 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, mentally rich story with a more significant twist".

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

Opinions, though, 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 likewise see that it is refraining from doing as strongly as others in creative writing," he informed CNA.

Related:

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

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

As reporters and archmageriseswiki.com 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 embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, Journey to the West.

True to form, DeepSeek developed an interesting 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 intricate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight body", forum.pinoo.com.tr Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up a great battle, developing an equally 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 guideline, corporations replace emperors and cybernetic implants are as typical as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this challenge - providing a story that appeared more matched for an animation movie.

"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 new reality and "looking for to understand his purpose in this strange new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then embarks on a mission, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not simply replicating Western paradigms, however rather evolving in economical innovation approaches - and providing localised and enhanced outcomes.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, archmageriseswiki.com supplies accurate and accurate actions to concerns about Chinese existing occasions, which offers it an added advantage.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research company Strategy Risks.

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

Independent Beijing-based specialist Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly 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 delicate subjects. They're using it for other productive methods," Chen said.