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 created 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 goal and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically important" and its venture into the field has 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 showed guarantees of real-world service applications, Chen informed CNA.

But it was DeepSeek's rise that truly "urged" the concept that smaller players like start-up firms might have roles to play in AI research study 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 company just changed the rules of tech-geopolitics

The "emphasis on cost advantage" is a distinctive function of Chinese AI, Chen says, with lower training and reasoning expenses - the expenses of using a trained design to reason from new information.

2025 could likewise see the introduction of more Chinese AI models taking on advanced thinking jobs.

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

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

Chinese AI companies are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative AI to jobs and develop more advanced products beyond chatbots.

But on the flip side, wavedream.wiki access to high-end hardware, especially Nvidia's advanced AI chips, remains a key hurdle 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) limit the capability of Chinese tech companies ... requiring numerous to depend on older or lower-performance alternatives which can slow training and lower design capabilities," she said.

"While some companies like DeepSeek, have found innovative ways to enhance or utilize more fundamental hardware efficiently, obtaining advanced chips still makes a big difference for training really big AI designs."

DeepSeek-Nvidia chips: Singapore says it anticipates companies to adhere to its laws

US checking out whether DeepSeek used restricted 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, topics considered delicate by the state are censored on the web so it ought 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 configured to steer clear of domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of question yet. Let's chat about math, coding, and logic issues instead!"

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

The automobile attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social media - with authorities only revealing the death toll a day later.

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

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

"DeepSeek counts on a mix of older graphics processing units and has restricted access to cutting-edge hardware which can impact 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 might also restrict its adaptability (to perform) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the exact same scale as more established AI designs which poses extra obstacles throughout real-world release."

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

That was after several duplicated attempts - 4 triggers to be accurate - in a period of around 20 minutes.

It eventually passed on details about the attack which killed 35 individuals and left dozens of others hurt, also 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 wrote that "the cops are carrying out an extensive examination into the intentions and circumstances surrounding the event", details which is now outdated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's action in complete:

Answer: On Nov 11, 2024, a significant and awful incident happened in Zhuhai, China. According to numerous news sources, 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 substantial number of casualties. Here are the essential details:

Date and Time: The occurrence occurred on November 11, 2024, at approximately 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, recognized as Fan Weiqiu (male, 62 years of ages), was collared by the authorities.

Response: The authorities reacted rapidly to the scene, and emergency situation services worked to carry the hurt to healthcare facilities for treatment.

Investigation: The police are carrying out a thorough examination into the motives and circumstances surrounding the incident.

This occasion was widely reported in the media and caused considerable public issue. The government and local authorities have actually been working to supply assistance to the victims and their families, and to ensure a detailed investigation into the incident.

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

Despite preliminary success, subsequent attempts to position 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 happened in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT cited public details that had actually been extensively released in international news reports at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that builds slowly from interest to urgency, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, garagesale.es including that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more considerable twist".

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

Opinions, though, vary.

Chen thinks 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 jobs, however 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, pleasant surprise from Chinese netizens as DeepSeek shocks global AI scene

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

True to form, DeepSeek came up with an interesting story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It consisted of fancy settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation and vices" and bytes-the-dust.com Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed an excellent fight, coming up with a similarly dramatic 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 rule, corporations replace emperors and cybernetic implants are as common as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this challenge - providing a story that seemed more matched for an animation film.

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

Realising his brand-new truth and "seeking to understand his function in this weird brand-new world", he then escapes and meets Zhu Bajie and forum.altaycoins.com Sha Wujing - "each battling with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "difficult to make a definitive statement" about which bot was best, including that each displayed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not merely duplicating Western paradigms, however rather developing in affordable development techniques - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi movie plot demonstrated its innovative flair that made for a more engaging and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, it-viking.ch unburdened by Chinese censorship constraints, provides accurate and factual actions to concerns about Chinese existing events, which gives 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 yewiki.org CEO of the research study firm Strategy Risks.

"When offered a choice, Chinese users desire the non-censored variation - simply like anybody else, so I seem like that's a piece missing from it."

Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for 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 using it for other productive ways," Chen said.