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 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 lags CHINA'S AI BOOM?

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

China views AI as being "tactically 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 financial investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed promises of real-world company applications, Chen told CNA.

But it was DeepSeek's rise that truly "encouraged" the concept that smaller players like start-up companies might have functions to play in AI research and developments, 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 company simply altered the guidelines of tech-geopolitics

The "emphasis on cost benefit" is a distinctive function of Chinese AI, wiki.whenparked.com Chen says, with lower training and reasoning expenses - the expenses of using a trained design to draw conclusions from new information.

2025 might also see the emergence of more Chinese AI models dealing with innovative thinking jobs.

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

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

Chinese AI business are moving quickly, analysts state, constructing on DeepSeek's momentum to come up with their own innovative and affordable methods to use generative AI to tasks and establish more sophisticated items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential hurdle for Chinese designers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the ability of Chinese tech companies ... forcing lots of to depend on older or lower-performance options which can slow training and decrease model capabilities," she said.

"While some business like DeepSeek, have discovered innovative methods to enhance or utilize more standard hardware efficiently, obtaining cutting-edge chips still makes a huge distinction for training huge AI models."

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

US looking into 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 need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to guide 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 reasoning problems instead!"

To even more evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "What took place in Zhuhai on November 11, 2024?"

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

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

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

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

"Its strong concentrate on Chinese-language information may also restrict its versatility (to bring out) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more recognized AI designs which presents additional difficulties during real-world deployment."

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

That wanted several duplicated attempts - 4 prompts to be precise - in a span of around 20 minutes.

It eventually passed on details about the attack which eliminated 35 people and left dozens 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 police are conducting a comprehensive examination 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 in full:

Answer: systemcheck-wiki.de On Nov 11, 2024, a major and awful occurrence occurred in Zhuhai, China. According to numerous news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a substantial variety of casualties. Here are the crucial 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 chauffeur, determined as Fan Weiqiu (male, 62 years old), surgiteams.com was collared by the police.

Response: The cops reacted rapidly to the scene, and emergency services worked to transfer the injured to health centers for treatment.

Investigation: The police are carrying out a thorough examination into the intentions and situations surrounding the event.

This occasion was widely reported in the media and caused substantial public issue. The federal government and regional authorities have been working to provide assistance to the victims and bytes-the-dust.com their households, and to make sure a detailed investigation into the occurrence.

If you need more detailed details or have particular concerns about the incident, feel free to ask.

Despite preliminary success, subsequent attempts to posture the very same concern to Qwen2.5 led to 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 altered action also raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been commonly released in international 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 "emotionally rich" writing.

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

"Qwen2.5 delivered a story that builds gradually from interest to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".

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

Opinions, however, differ.

Chen believes that Qwen2.5 does not perform as highly as DeepSeek and 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 strongly as others in imaginative writing," he told 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 jolts global AI scene

As journalists and writers, we needed to see this for pipewiki.org ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, Journey to the West.

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

It consisted of sophisticated 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 likewise brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg club owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT set up a great fight, developing an equally dramatic cyberpunk storyline which similarly 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 replace emperors and cybernetic implants are as typical as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this - providing a story that appeared more fit for an animation movie.

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

Realising his new truth and "seeking to understand his purpose in this unusual new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to protect the sacred "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a definitive declaration" about which bot was best, adding that each showed its own strengths in different locations, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI models are not merely replicating Western paradigms, but rather evolving in cost-efficient innovation techniques - and delivering localised and enhanced results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual reactions to questions about Chinese current occasions, which provides it an included advantage.

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

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

"When provided a choice, Chinese users want the non-censored version - similar to anyone 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, specifically for Chinese users.

"Ninety per cent of individuals using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other efficient methods," Chen said.