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 produced 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 becoming the world leader in AI by 2030.

China views AI as being "tactically essential" and its foray into the field has 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 took off in 2022 and showed pledges of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that really "urged" the idea that smaller gamers like start-up companies 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 model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business simply altered the rules of tech-geopolitics

The "emphasis on expense benefit" is an unique feature of Chinese AI, Chen states, with lower training and inference costs - the costs of using a trained model to reason from brand-new data.

2025 could also see the emergence of more Chinese AI models taking on advanced 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 models and integrate them with scientific research," Chen included.

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

Chinese AI companies are moving quickly, experts say, building on DeepSeek's momentum to come up with their own innovative and affordable methods to use generative AI to jobs and establish advanced products beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a crucial obstacle for Chinese developers, 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 capability of Chinese tech business ... requiring lots of to rely on older or lower-performance alternatives which can slow training and lower model capabilities," she said.

"While some business like DeepSeek, have found innovative methods to optimize or use more basic hardware efficiently, obtaining cutting-edge chips still makes a big difference for training huge AI models."

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

US checking out whether DeepSeek utilized restricted 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, subjects deemed sensitive by the state are censored on the internet so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what took place 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 type of concern yet. Let's chat about math, coding, and logic problems instead!"

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

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

DeepSeek failed to discuss that an attack had occurred, highlighting instead a military air show and other events that had taken place in the city like singles' day shopping sales in addition to sports and cultural activities.

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

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

"Its strong concentrate on Chinese-language information may likewise restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been tested as broadly or on the exact same scale as more recognized AI models which postures additional obstacles during real-world implementation."

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

That wanted several repeated efforts - four triggers to be precise - in a period of around 20 minutes.

It eventually passed on details about the attack which eliminated 35 people and left lots of others injured, 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 cops are carrying out a comprehensive investigation into the motives and circumstances surrounding the incident", details which is now obsoleted.

The motorist, Fan, was carried out last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and tragic event took place in Zhuhai, China. According to numerous news sources, 89u89.com a man named Fan Weiqiu (樊某, male, 62 years old) 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 event 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 motorist, identified as Fan Weiqiu (male, 62 years of ages), was nabbed by the police.

Response: The cops reacted quickly to the scene, and emergency services worked to transfer the hurt to medical facilities for treatment.

Investigation: The police are conducting a comprehensive investigation into the intentions and situations surrounding the event.

This occasion was widely reported in the media and triggered substantial public issue. The federal government and regional authorities have been working to provide support to the victims and their households, and to ensure a detailed investigation into the event.

If you require more detailed details or have specific concerns about the occurrence, feel totally free to ask.

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

The altered action likewise raised concerns about its consistency and reliability.

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

WHICH IS MORE CREATIVE?

Users have actually praised the ability 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 writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that develops gradually from interest to urgency, 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, including that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more significant twist".

"DeepSeek composed a good story however did not have tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, however, differ.

Chen believes that Qwen2.5 does not perform as strongly 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 highly as others in innovative writing," he told CNA.

Related:

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

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks worldwide 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 set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created an appealing storyline embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

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

It also remarkably reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken 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 battle, coming up with an equally significant cyberpunk story which similarly 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 common as ancient myths."

Disappointingly, Qwen2.5 fell short in this obstacle - delivering a story that appeared more matched for an animation movie.

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

Realising his brand-new reality and "looking for to comprehend his function in this strange brand-new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "tough to make a definitive declaration" about which bot was best, adding that each displayed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not merely duplicating Western paradigms, however rather progressing in cost-effective development techniques - and delivering localised and enhanced results.

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

DeepSeek's sci-fi film plot showed its innovative flair that produced a more engaging and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate responses to concerns about Chinese existing events, which provides it an included advantage.

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

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

"When given an option, Chinese users desire the non-censored variation - similar to anybody else, so I seem 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 per cent of individuals utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other productive methods," Chen said.