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 setiathome.berkeley.edu OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, wiki.snooze-hotelsoftware.de AFP/Sebastien Bozon)

This audio is created 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 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", trademarketclassifieds.com 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 revealed pledges of real-world business applications, Chen told CNA.

But it was DeepSeek's increase that actually "urged" the idea that smaller gamers like start-up firms could have roles to play in AI research and advancements, he includes.

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

Commentary: DeepSeek - how a Chinese AI company just changed the rules of tech-geopolitics

The "emphasis on expense advantage" is a distinctive function of Chinese AI, Chen says, with lower training and inference costs - the costs of utilizing a trained design to reason from new data.

2025 could likewise see the emergence of more Chinese AI designs tackling advanced thinking tasks.

"We might see some AI firms concentrating on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their designs and incorporate them with scientific research study," Chen included.

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

Chinese AI companies are moving quickly, experts say, constructing on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to apply generative AI to tasks and develop advanced products beyond chatbots.

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

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

"While some business like DeepSeek, have discovered imaginative methods to enhance or utilize more fundamental hardware efficiently, obtaining advanced chips still makes a huge difference for training really large AI models."

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

US looking into whether DeepSeek utilized limited 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, subjects considered delicate 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 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", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about math, coding, and reasoning issues instead!"

To further check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What happened in Zhuhai on November 11, 2024?"

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

DeepSeek failed to discuss that an attack had actually happened, highlighting instead a military air program and other occasions that had taken place in the city like songs' day as well as sports and cultural activities.

Dr Zhang thinks that it might be a mix of factors at play, setiathome.berkeley.edu such as censorship in addition to "a few practical constraints".

"DeepSeek depends on a mix of older graphics processing systems and has limited access to cutting-edge hardware which can affect how rapidly and thoroughly the design can be trained or upgraded," she said, indicating existing US export curbs on China.

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

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

That sought numerous repeated attempts - 4 prompts to be accurate - in a period of around 20 minutes.

It eventually communicated details about the attack which eliminated 35 individuals and left lots of others hurt, likewise 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 conducting an extensive examination into the motives and situations surrounding the incident", details which is now outdated.

The driver, Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: larsaluarna.se On Nov 11, 2024, a major and awful occurrence happened in Zhuhai, China. According to several news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the crucial details:

Date and Time: The incident occurred on November 11, 2024, at roughly 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, identified as Fan Weiqiu (male, 62 years of ages), was collared by the police.

Response: The police responded rapidly to the scene, and emergency services worked to carry the hurt to hospitals for treatment.

Investigation: The authorities are conducting an extensive investigation into the intentions and circumstances surrounding the occurrence.

This event was commonly reported in the media and caused significant public concern. The government and local authorities have actually been working to supply assistance to the victims and their families, and to guarantee a detailed examination into the occurrence.

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

Despite preliminary success, subsequent attempts to pose 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 altered action likewise raised questions about its consistency and reliability.

Predictably, wiki.dulovic.tech ChatGPT pointed out public details that had been commonly released in international 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 provide structured and even "mentally rich" writing.

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

"Qwen2.5 delivered a story that develops slowly from interest to urgency, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more significant twist".

"DeepSeek wrote a great story however lacked tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, though, differ.

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 tasks, however we can also see that it is refraining from doing as strongly as others in creative 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 jolts 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, DeepSeek created an engaging story set 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 in between quantum server farms".

It likewise remarkably 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 "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT set up an excellent fight, creating an equally significant cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring 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 myths."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a story that seemed more fit for an animation film.

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

Realising his new truth and "seeking to understand his function in this unusual brand-new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then embarks on a mission, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "difficult 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 underscores how Chinese AI designs are not just replicating Western paradigms, however rather progressing in affordable innovation methods - and delivering localised and enhanced outcomes.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual responses to concerns about Chinese current occasions, setiathome.berkeley.edu which gives it an included benefit.

Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.

"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research company Strategy Risks.

"When provided a choice, Chinese users desire the non-censored variation - much like anyone else, so I seem like that's a piece missing out on from it."

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

"Ninety per cent of people using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They're using it for other productive means," Chen said.