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 nation 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 "tactically important" and its foray into the field has actually been "years in the making", said Chen Qiheng, an associated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed guarantees of real-world business applications, Chen informed CNA.

But it was DeepSeek's rise that really "encouraged" the concept that smaller players like start-up firms might have roles 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 just altered the guidelines of tech-geopolitics

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

2025 might likewise see the introduction of more Chinese AI designs tackling sophisticated thinking tasks.

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

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

Chinese AI companies are moving quickly, analysts state, constructing on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to apply generative AI to tasks and establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a key difficulty for Chinese designers, noted 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 business ... forcing many to depend on older or lower-performance options which can slow training and decrease design abilities," she said.

"While some business like DeepSeek, have actually discovered creative ways to enhance or use more basic hardware effectively, obtaining advanced chips still makes a big difference for training huge AI models."

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

US looking into whether DeepSeek used 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, 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 inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to avoid 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 logic problems rather!"

To even more check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact 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 on.

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

Dr Zhang believes that it may be a mix of elements at play, such as censorship in addition to "a few practical constraints".

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

"Its strong concentrate on Chinese-language data might likewise limit its versatility (to perform) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the exact same scale as more recognized AI models which poses additional difficulties during real-world deployment."

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

That wanted several duplicated efforts - 4 triggers to be precise - in a span of around 20 minutes.

It eventually communicated details about the attack which killed 35 individuals and left dozens of others hurt, 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 thorough investigation into the intentions and scenarios surrounding the incident", details which is now outdated.

The motorist, Fan, was executed last month.

This is Qwen2.5's reaction in full:

Answer: On Nov 11, 2024, a major and tragic event occurred in Zhuhai, China. According to multiple news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the key details:

Date and Time: The occurrence occurred on November 11, 2024, at roughly 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: pipewiki.org The attack led to 35 deaths and 43 injuries.

Perpetrator: The driver, identified as Fan Weiqiu (male, 62 years old), was captured by the authorities.

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

Investigation: The cops are performing a thorough investigation into the intentions and circumstances surrounding the incident.

This occasion was widely reported in the media and triggered substantial public issue. The government and regional authorities have actually been working to supply support to the victims and their households, and to guarantee a detailed examination into the incident.

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

Despite preliminary success, subsequent efforts to pose the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on occasions that took place in Zhuhai on November 11, 2024".

The modified action likewise raised questions about its consistency and reliability.

Predictably, ChatGPT cited public details that had 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 deliver structured and even "emotionally abundant" writing.

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

"Qwen2.5 delivered a story that builds slowly from interest to urgency, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more substantial twist".

"DeepSeek composed an excellent story but did not have stress and an impactful climax, making Qwen2.5 the evident option."

Opinions, however, vary.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can also see that it is refraining from doing as strongly as others in innovative writing," he informed CNA.

Related:

China's brand-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 journalists and authors, 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, featuring main characters from the classic Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created an engaging 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 fancy settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float 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 taken fight 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 become waterlogged and fragmented".

ChatGPT put up an excellent battle, coming up with a similarly dramatic cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".

"This is a world where AI deities guideline, corporations change emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this challenge - providing a storyline that appeared more suited for an animation film.

"The film begins with the awakening of Sun Wukong within a high-tech research center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his new truth and "looking for to understand his purpose in this strange new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then embarks on a quest, navigating the streets of Chongqing to protect the sacred "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a conclusive statement" 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 designs are not just replicating Western paradigms, however rather developing in cost-effective development methods - and delivering localised and improved results.

In our tests, engel-und-waisen.de each bot showcased their own distinct strengths, which certainly made direct comparisons challenging.

DeepSeek's sci-fi motion picture plot showed its imaginative flair that produced a more engaging and creative story as compared to Qwen2.5 and wiki.snooze-hotelsoftware.de ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate reactions to questions about Chinese existing events, which gives it an included benefit.

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

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

"When provided an option, Chinese users want the non-censored variation - just 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, 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 topics. They're utilizing it for other productive means," Chen said.