How do Chinese AI bots stack up against ? 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'S BEHIND CHINA'S AI BOOM?

Transforming the country into a tech superpower has long been President Xi Jinping's objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically crucial" 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 financial investments in Chinese AI sped up after ChatGPT removed in 2022 and showed pledges of real-world business applications, Chen told CNA.

But it was DeepSeek's rise that actually "urged" the idea that smaller players like start-up companies might have functions to play in AI research and developments, he adds.

'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 company just changed the guidelines of tech-geopolitics

The "emphasis on expense benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning costs - the costs of using a trained design to draw conclusions from new data.

2025 could also see the development of more Chinese AI models tackling innovative thinking jobs.

"We could see some AI companies focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with scientific research," Chen included.

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

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

But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains an essential obstacle for Chinese developers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the capability of Chinese tech business ... forcing many to count on older or lower-performance alternatives which can slow training and reduce design capabilities," she said.

"While some business like DeepSeek, have actually found creative methods to optimize or utilize more basic hardware effectively, obtaining cutting-edge chips still makes a big distinction for training large AI models."

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

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

Tests recommend Chinese chatbots are configured 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 question yet. Let's chat about mathematics, coding, and logic problems rather!"

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

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

DeepSeek failed to mention that an attack had happened, highlighting rather a military air program and other events that had happened 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 elements at play, such as censorship as well as "a few useful constraints".

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

"Its strong concentrate on Chinese-language information may also limit its versatility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been checked as broadly or on the very same scale as more recognized AI models which positions extra challenges during real-world release."

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

That sought several repeated efforts - 4 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 list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that "the cops are conducting an extensive investigation into the motives and scenarios surrounding the occurrence", details which is now outdated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and awful event took place 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, resulting in a significant variety of casualties. Here are the key details:

Date and Time: The event happened 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, recognized as Fan Weiqiu (male, 62 years of ages), was nabbed by the cops.

Response: The authorities reacted quickly to the scene, and emergency situation services worked to transfer the injured to health centers for treatment.

Investigation: genbecle.com The cops are conducting an extensive investigation into the motives and circumstances surrounding the occurrence.

This occasion was commonly reported in the media and caused substantial public concern. The federal government and local authorities have been working to provide assistance to the victims and their households, and to ensure a detailed investigation into the occurrence.

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

Despite preliminary success, subsequent attempts to position the very same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on events that took place in Zhuhai on November 11, 2024".

The altered response also raised questions about its consistency and dependability.

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

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that constructs gradually from interest to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more considerable twist".

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

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 tasks, but we can also see that it is refraining from doing as strongly 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, enjoyable surprise from Chinese netizens as DeepSeek jolts global 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 film plot embeded in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore impressive, Journey to the West.

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

It included sophisticated settings - smoggy skies "pierced by high-rise buildings", "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 "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg nightclub 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, creating a similarly remarkable 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 obstacle - delivering a storyline that appeared more suited for an animation film.

"The motion picture begins with the awakening of Sun Wukong within a state-of-the-art research facility situated 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 strange brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, navigating 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 "hard to make a definitive declaration" about which bot was best, including that each displayed its own strengths in different locations, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI designs are not just replicating Western paradigms, but rather developing in economical development approaches - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi motion picture plot demonstrated its innovative flair that produced a more appealing 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 factual responses to concerns about Chinese existing events, which gives it an added advantage.

Experts likewise weighed in on their ideas after using 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 firm Strategy Risks.

"When offered a choice, Chinese users desire the non-censored variation - similar to anyone else, so I feel like that's a piece missing 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 utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other productive means," Chen said.