aiot-7

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 startup 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 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 essential" and its foray into the field has actually 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 investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed pledges of real-world business applications, Chen told CNA.

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

'A lot is up in the air': Is Chinese company DeepSeek's AI model 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 distinct function of Chinese AI, Chen says, with lower training and reasoning costs - the expenses of using a trained model to draw conclusions from brand-new information.

2025 could also see the emergence of more Chinese AI models taking on sophisticated thinking jobs.

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

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

Chinese AI companies are moving quickly, experts say, constructing on DeepSeek's momentum to come up with their own ingenious and economical ways to apply generative AI to jobs and establish more innovative products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a crucial hurdle 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 companies ... forcing numerous to count on older or lower-performance options which can slow training and lower design abilities," she said.

"While some business like DeepSeek, have discovered imaginative methods to enhance or use more fundamental hardware efficiently, obtaining innovative chips still makes a huge difference for training huge AI models."

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

US checking out whether DeepSeek used restricted AI chips obtained through other nations, source states

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 disputes or tell you what occurred 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 kind of concern yet. Let's chat about mathematics, coding, and logic problems rather!"

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

The vehicle attack outside a sports arena in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities only disclosing the death toll a day later on.

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

Dr Zhang thinks that it might be a mix of aspects at play, such as censorship in addition to "a few practical constraints".

"DeepSeek counts on a mix of older graphics processing units and has actually restricted access to cutting-edge hardware which can affect how rapidly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data may likewise restrict its adaptability (to carry out) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the very same scale as more recognized AI models which poses additional difficulties during real-world implementation."

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

That was after multiple duplicated attempts - 4 prompts to be accurate - in a span of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 individuals and left lots of others injured, likewise going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it composed that "the cops are carrying out a comprehensive examination into the motives and situations surrounding the incident", details which is now outdated.

The motorist, Fan, was executed last month.

This is Qwen2.5's reaction in complete:

Answer: On Nov 11, 2024, a major and tragic event took place in Zhuhai, China. According to multiple news sources, a guy called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the essential 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 resulted in 35 deaths and 43 injuries.

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

Response: The authorities responded rapidly to the scene, and emergency services worked to transport the hurt to medical facilities for treatment.

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

This event was widely reported in the media and triggered substantial public concern. The government and regional authorities have actually been working to provide assistance to the victims and their families, and to make sure a detailed examination into the incident.

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

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

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

Predictably, ChatGPT mentioned public details that had actually been commonly published in worldwide report 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 "emotionally rich" writing.

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

"Qwen2.5 provided a story that constructs gradually from interest to urgency, keeping the reader engaged. It provides an unanticipated 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 however lacked tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, however, vary.

Chen thinks that Qwen2.5 does not carry out as highly as DeepSeek and bytes-the-dust.com ChatGPT when it pertains to creative writing.

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

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts international AI scene

As reporters and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi movie plot set in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek created an engaging storyline embeded 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 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 stolen fight body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up an excellent battle, developing an equally remarkable cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring 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 misconceptions."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a storyline that appeared more matched 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 truth and "looking for to understand his purpose in this odd brand-new world", he then leaves and satisfies 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 safeguard the sacred "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not just duplicating Western paradigms, but rather evolving in cost-efficient innovation approaches - and providing localised and enhanced results.

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

DeepSeek's sci-fi motion picture 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 recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and surgiteams.com factual responses to concerns about Chinese current occasions, which provides it an added benefit.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, and CEO of the research firm Strategy Risks.

"When provided an option, Chinese users desire the non-censored variation - much 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 ratemywifey.com Chinese users.

"Ninety per cent of people using the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other efficient means," Chen said.