How do Chinese aI Bots Stack up Against ChatGPT?

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 crucial” and its venture into the field has 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 removed in 2022 and setiathome.berkeley.edu revealed pledges of real-world company applications, Chen told CNA.

But it was DeepSeek’s increase that actually “encouraged” the idea that smaller sized gamers like start-up firms could have roles to play in AI research study and developments, 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 altered the rules of tech-geopolitics

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

2025 could also see the development of more Chinese AI designs taking on advanced thinking tasks.

“We might see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete methods to commercialise their models and incorporate them with clinical research study,” Chen added.

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

Chinese AI business are moving rapidly, experts say, developing on DeepSeek’s momentum to come up with their own innovative and cost-efficient ways to apply generative AI to jobs and establish advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia’s advanced AI chips, wavedream.wiki remains an essential obstacle for Chinese designers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney’s (UTS) Australia-China Relations Institute.

“US export controls (still) restrict the ability of Chinese tech companies … requiring many to count on older or lower-performance alternatives which can slow training and decrease design capabilities,” she said.

“While some companies like DeepSeek, have discovered innovative methods to enhance or use more standard hardware effectively, obtaining advanced chips still makes a huge distinction for training large AI models.”

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

US looking into whether DeepSeek utilized limited AI chips obtained through other countries, 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, topics deemed delicate by the state are censored on the web so it must come as no surprise that Chinese-made chatbots will not territorial disagreements or inform you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to guide clear of 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 logic problems instead!”

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

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

DeepSeek failed to point out that an attack had taken location, highlighting rather a military air show and other events that had actually occurred in the city like singles’ 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 as well as “a couple of practical constraints”.

“DeepSeek relies on a mix of older graphics processing systems and has limited access to cutting-edge hardware which can affect how rapidly and extensively the model can be trained or upgraded,” 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 checked as broadly or on the exact same scale as more established AI designs which presents extra challenges throughout real-world release.”

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

That was after numerous repeated efforts – 4 triggers to be exact – in a period of around 20 minutes.

It eventually communicated details about the attack which eliminated 35 people and left dozens of others injured, 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 composed that “the authorities are conducting a comprehensive investigation into the intentions and circumstances surrounding the event”, details which is now dated.

The driver, Fan, was performed last month.

This is Qwen2.5’s response in complete:

Answer: On Nov 11, 2024, a significant and tragic event occurred in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a substantial number of casualties. Here are the key details:

Date and Time: The incident happened on November 11, 2024, at approximately 19:48 PM.

Location: bio.rogstecnologia.com.br 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 captured by the authorities.

Response: The cops reacted rapidly to the scene, and emergency situation services worked to transfer the injured to medical facilities for treatment.

Investigation: The police are carrying out an extensive investigation into the intentions and circumstances surrounding the occurrence.

This occasion was widely reported in the media and triggered considerable public concern. The government and regional authorities have been working to offer 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 concerns about the incident, feel totally free to ask.

Despite initial success, subsequent attempts to pose the same question to Qwen2.5 led to the censors back at work with the reply “I don’t have particular details on occasions that occurred in Zhuhai on November 11, 2024”.

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

Predictably, ChatGPT cited public details that had actually been extensively published in global report at the time of the mishap – so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to provide structured and even “mentally rich” writing.

“DeepSeek-R1 used 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 provided a story that builds gradually from curiosity to seriousness, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting,” she said, adding that Qwen2.5 eventually “crafted a more cinematic, emotionally rich story with a more substantial twist”.

“DeepSeek composed a great story but did not have stress and an impactful climax, making Qwen2.5 the obvious option.”

Opinions, though, vary.

Chen thinks 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 jobs, but we can likewise 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 needed to see this for ourselves so we put each bot to the test – to come up with a standard sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created an interesting storyline 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 high-rise buildings”, “holographic lanterns that float above neon-lit streets” and “ancient temples nestled between quantum server farms”.

It also brilliantly reimagined traditional 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 “silent hulking android” from the Yangtze River, whose “memory cores become waterlogged and fragmented”.

ChatGPT put up an excellent fight, creating a similarly significant 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 rule, corporations replace emperors and cybernetic implants are as common as ancient misconceptions.”

Disappointingly, Qwen2.5 fell short in this difficulty – providing a story that seemed more matched for an animation movie.

“The film 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 new reality and “seeking to comprehend his function in this odd brand-new world”, wiki.asexuality.org he then gets away and meets Zhu Bajie and Sha Wujing – “each having problem with their own existential crises”.

The trio then embarks on a mission, browsing the streets of Chongqing to protect the spiritual “Eternal Scroll” from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was “tough to make a definitive declaration” about which bot was best, adding 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 merely duplicating Western paradigms, however rather developing in cost-efficient development methods – and providing localised and enhanced results.

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

DeepSeek’s sci-fi movie 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, supplies accurate and factual reactions to questions about Chinese current occasions, which offers it an added advantage.

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

“DeepSeek is at a drawback when it pertains to censorship constraints,” noted Isaac Stone Fish, creator and CEO of the research study firm Strategy Risks.

“When given a choice, Chinese users want the non-censored version – simply like anyone else, so I feel 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, particularly for Chinese users.

“Ninety percent of individuals using the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They’re using it for other efficient ways,” Chen said.