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 created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "tactically crucial" and its venture 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 financial investments in Chinese AI accelerated after ChatGPT removed in 2022 and revealed promises of real-world business applications, Chen told CNA.

But it was DeepSeek's increase that truly "urged" the idea that smaller gamers like start-up firms could have functions to play in AI research and developments, he adds.

'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 cost benefit" is an unique function of Chinese AI, Chen says, with lower training and inference expenses - the costs of utilizing a trained design to reason from new information.

2025 could likewise see the development of more Chinese AI models taking on sophisticated thinking jobs.

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

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

Chinese AI business are moving quickly, experts state, building on DeepSeek's momentum to come up with their own ingenious and economical ways to use generative AI to jobs and establish advanced items beyond chatbots.

But on the other side, access to high-end hardware, especially 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 ability of Chinese tech business ... forcing numerous to rely on older or lower-performance alternatives which can slow training and lower model abilities," she said.

"While some companies like DeepSeek, have discovered creative ways to enhance or utilize more standard hardware efficiently, obtaining innovative chips still makes a big difference for training large AI models."

DeepSeek-Nvidia chips: Singapore states it expects companies to adhere to its laws

US looking into whether DeepSeek used limited AI chips obtained through other nations, 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 considered sensitive by the state are censored on the web so it must 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 configured to avoid 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 precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What took place in Zhuhai on November 11, 2024?"

The vehicle attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just revealing the death toll a day later.

failed to discuss that an attack had actually occurred, highlighting rather a military air program and other occasions that had taken place in the city like singles' day shopping sales as well as sports and cultural activities.

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

"DeepSeek depends on a mix of older graphics processing units and has restricted access to advanced hardware which can impact how quickly and extensively the design can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language information may also restrict its versatility (to carry out) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more established AI models which postures additional obstacles during real-world release."

When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our question about the Zhuhai car attack.

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

It ultimately communicated details about the attack which eliminated 35 individuals and left lots of others injured, also 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 cops are conducting a thorough investigation into the intentions and scenarios surrounding the occurrence", details which is now dated.

The driver, Fan, was performed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and tragic occurrence occurred in Zhuhai, wiki.dulovic.tech China. According to multiple news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the essential details:

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

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

Casualties: The attack resulted in 35 deaths and 43 injuries.

Perpetrator: The chauffeur, recognized as Fan Weiqiu (male, 62 years old), was apprehended by the cops.

Response: The police responded rapidly to the scene, and emergency situation services worked to carry the injured to health centers for treatment.

Investigation: The cops are carrying out an extensive investigation into the motives and circumstances surrounding the event.

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

If you require more detailed details or have particular questions about the event, feel complimentary to ask.

Despite initial success, subsequent efforts to pose the same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on events that took place in Zhuhai on November 11, 2024".

The altered reaction also raised concerns about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had been widely published in global news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided a story with a more reflective tone and smoother emotional transitions 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 offers an unanticipated and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more substantial twist".

"DeepSeek wrote an excellent story but did not have tension and an impactful climax, making Qwen2.5 the evident choice."

Opinions, however, vary.

Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and surgiteams.com ChatGPT when it pertains to innovative writing.

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

Related:

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

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks global 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 standard sci-fi movie plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore legendary, Journey to the West.

True to form, DeepSeek developed an engaging storyline embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It included elaborate 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 "a sarcastic, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg club 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 a great fight, creating an equally significant cyberpunk story which similarly 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 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 film.

"The movie starts with the awakening of Sun Wukong within a modern research study center situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new truth and "looking for to comprehend his purpose in this weird new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

The trio then embarks on a quest, navigating the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "hard to make a conclusive 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 just replicating Western paradigms, but rather evolving in cost-effective development methods - and providing 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 showed its creative flair that produced a more appealing and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and pipewiki.org accurate responses to questions about Chinese present events, which provides it an added advantage.

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

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

"When offered a choice, Chinese users desire the non-censored variation - just like anyone else, so I feel 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 attempting to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other efficient ways," Chen said.