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 country into a tech superpower has actually 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 important" and its venture 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 removed in 2022 and showed guarantees of real-world business applications, Chen informed CNA.

But it was DeepSeek's increase that really "urged" the idea that smaller sized players like start-up companies might have roles to play in AI research study and it-viking.ch developments, he includes.

'A lot is up in the air': demo.qkseo.in Is Chinese firm DeepSeek's AI model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business just changed the rules of tech-geopolitics

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

2025 could also see the emergence of more Chinese AI designs taking on innovative thinking tasks.

"We might see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with clinical research study," Chen included.

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

Chinese AI business are moving quickly, analysts state, constructing on DeepSeek's momentum to come up with their own innovative and economical ways to apply generative AI to tasks and develop advanced items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial difficulty 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) limit the capability of Chinese tech companies ... forcing lots of to rely on older or lower-performance options which can slow training and reduce design capabilities," she said.

"While some business like DeepSeek, have discovered imaginative methods to optimize or utilize more standard hardware efficiently, obtaining innovative chips still makes a big distinction for training large AI models."

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

US looking into whether DeepSeek used limited AI chips obtained through other countries, source says

So how do Chinese AI bots match up 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 internet so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to guide clear of domestic politics.

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

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

The cars and truck attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social networks - 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 happened in the city like songs' day shopping sales in addition to sports and cultural activities.

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

"DeepSeek counts on a mix of older graphics processing systems and has actually restricted access to advanced hardware which can impact how quickly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data might likewise 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 postures additional challenges throughout real-world deployment."

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

That sought multiple repeated attempts - four prompts to be precise - in a span of around 20 minutes.

It ultimately relayed details about the attack which eliminated 35 people 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, along with casualties.

However, it composed that "the authorities are conducting an extensive investigation into the intentions and scenarios surrounding the occurrence", details which is now outdated.

The driver, Fan, was performed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and terrible incident occurred in Zhuhai, wiki.myamens.com China. According to several news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the key details:

Date and Time: The incident happened on November 11, 2024, at approximately 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 captured by the police.

Response: The police reacted quickly to the scene, and emergency worked to carry the hurt to healthcare facilities for treatment.

Investigation: The police are performing a thorough examination into the motives and scenarios surrounding the occurrence.

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

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

Despite initial success, subsequent attempts to present the very same question 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 modified response likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had actually been widely published in worldwide report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the ability of Chinese AI apps to deliver structured and even "emotionally abundant" writing.

"DeepSeek-R1 offered a story with a more introspective 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 constructs slowly from interest to urgency, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more substantial twist".

"DeepSeek wrote an excellent story however lacked stress and an impactful climax, making Qwen2.5 the obvious option."

Opinions, however, differ.

Chen thinks that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can likewise 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, enjoyable surprise from Chinese netizens as DeepSeek jolts international AI scene

As reporters and authors, we had 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, featuring main characters from the classic Chinese folklore legendary, Journey to the West.

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

It consisted of elaborate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise brilliantly reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken battle body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed a good fight, creating an equally significant cyberpunk storyline 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 change emperors and cybernetic implants are as typical as ancient myths."

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

"The motion picture starts with the awakening of Sun Wukong within a modern research study facility located 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 purpose in this odd new world", he then escapes and surgiteams.com satisfies Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard to make a conclusive 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 duplicating Western paradigms, but rather evolving in cost-effective development methods - and delivering localised and enhanced outcomes.

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

DeepSeek's sci-fi film plot showed its imaginative flair that made for a more appealing and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual responses to questions about Chinese current events, engel-und-waisen.de which offers it an included advantage.

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

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

"When offered a choice, Chinese users desire the non-censored variation - much like anybody else, so I feel like that's a piece missing out on 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 deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other productive means," Chen said.