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 generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the country into a tech superpower has actually 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 important" and its foray 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 investments in Chinese AI accelerated after ChatGPT removed in 2022 and showed guarantees of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that actually "encouraged" the concept that smaller players like start-up companies could have roles to play in AI research and advancements, he adds.

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

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

The "emphasis on expense advantage" is an unique function of Chinese AI, Chen says, with lower training and inference costs - the expenses of using a trained model to draw conclusions from brand-new information.

2025 might also see the emergence of more Chinese AI models taking on advanced thinking jobs.

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

AGI describes a system with intelligence on par with human capabilities.

Chinese AI companies are moving rapidly, analysts state, developing on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to apply generative AI to jobs and establish more sophisticated products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a crucial obstacle for Chinese designers, 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 ... requiring lots of to count on older or lower-performance options which can slow training and decrease design abilities," she said.

"While some companies like DeepSeek, have actually found innovative methods to enhance or use more standard hardware efficiently, obtaining advanced chips still makes a huge distinction for training extremely large AI models."

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

US looking into whether DeepSeek used restricted AI chips obtained through other nations, 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, subjects deemed delicate by the state are censored on the internet 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 programmed to steer clear of 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 mathematics, coding, and logic problems rather!"

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

The vehicle attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities just divulging the death toll a day later on.

DeepSeek failed to mention that an attack had occurred, highlighting rather a military air show and other events that had occurred in the city like songs' day shopping sales in addition to sports and cultural activities.

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

"DeepSeek depends on a mix of older graphics processing units and has actually limited access to innovative hardware which can impact how rapidly and extensively the model can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data might likewise restrict its adaptability (to perform) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been checked as broadly or on the very same scale as more established AI designs which poses additional challenges during real-world release."

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

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

It eventually communicated details about the attack which killed 35 individuals and yewiki.org left lots of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that "the authorities are conducting an extensive examination into the motives and situations surrounding the incident", details which is now dated.

The motorist, Fan, was executed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major and awful incident took place in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the essential details:

Date and Time: The occurrence took place 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 chauffeur, recognized as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

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

Investigation: The cops are conducting a comprehensive examination into the intentions and circumstances surrounding the incident.

This occasion was extensively reported in the media and triggered significant public concern. The federal government and local authorities have been working to provide assistance to the victims and their families, and to guarantee a detailed examination into the incident.

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

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

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

Predictably, ChatGPT mentioned public details that had been commonly released in global report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that builds slowly from interest to urgency, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more considerable twist".

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

Opinions, though, differ.

Chen believes that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to creative writing.

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

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

As reporters and writers, we had 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, including main characters from the classic Chinese folklore epic, Journey to the West.

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

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

It also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat 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 become waterlogged and fragmented".

ChatGPT installed a great battle, coming up with a similarly 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 change emperors and cybernetic implants are as common as ancient myths."

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

"The movie starts 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 brand-new truth and "seeking to comprehend his purpose in this weird brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each dealing 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 kept in mind that it was "tough to make a conclusive statement" about which bot was best, including that each displayed its own strengths in different locations, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI designs are not merely reproducing Western paradigms, but rather evolving in cost-effective innovation approaches - and delivering localised and improved outcomes.

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

DeepSeek's sci-fi film plot showed its creative flair that made for 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 precise and factual actions to questions about Chinese present occasions, which offers it an added benefit.

Experts also weighed in on their thoughts 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 study company Strategy Risks.

"When given an option, Chinese users want the non-censored variation - similar to anyone else, so I seem 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, specifically 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 topics. They're utilizing it for other efficient ways," Chen said.