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 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 objective 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 foray into the field has been "years in the making", said Chen Qiheng, an affiliated scientist 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 revealed promises of real-world organization applications, Chen informed CNA.

But it was DeepSeek's increase that actually "urged" the idea that smaller gamers like start-up firms might have functions to play in AI research and advancements, 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 rules of tech-geopolitics

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

2025 could likewise see the development of more Chinese AI designs taking on advanced reasoning tasks.

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

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

Chinese AI business are moving rapidly, experts say, constructing on DeepSeek's momentum to come up with their own ingenious and disgaeawiki.info cost-effective methods to use generative AI to jobs and establish more sophisticated products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a crucial difficulty for Chinese developers, noted Dr Marina Zhang, archmageriseswiki.com an associate professor 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 count on older or lower-performance alternatives which can slow training and decrease model capabilities," she said.

"While some companies like DeepSeek, have actually found innovative ways to optimize or use more basic hardware effectively, obtaining innovative chips still makes a huge difference for training large AI models."

DeepSeek-Nvidia chips: Singapore says it expects business to comply with its laws

US looking into whether DeepSeek used limited AI chips obtained through other countries, 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, subjects deemed delicate by the state are censored on the internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed to avoid 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 math, coding, and logic problems instead!"

To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the 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 at first heavily censored on Chinese social networks - with authorities just divulging the death toll a day later.

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

Dr Zhang thinks that it might be a mix of factors at play, such as censorship as well as "a few practical constraints".

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

"Its strong focus on Chinese-language information might also limit its adaptability (to carry out) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been evaluated as broadly or on the same scale as more recognized AI designs which presents additional obstacles throughout real-world implementation."

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

That was after multiple duplicated efforts - 4 prompts to be precise - in a period of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 people and left dozens of others hurt, also going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it wrote that "the police are conducting a comprehensive examination into the intentions and circumstances surrounding the incident", details which is now obsoleted.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's response in full:

Answer: On Nov 11, 2024, a significant and awful event took place in Zhuhai, China. According to numerous news sources, engel-und-waisen.de a man named Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a substantial 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 resulted in 35 deaths and 43 injuries.

Perpetrator: The driver, identified as Fan Weiqiu (male, 62 years of ages), was apprehended by the cops.

Response: The cops reacted rapidly to the scene, and emergency services worked to transport the injured to hospitals for treatment.

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

This occasion was extensively reported in the media and caused substantial public concern. The government and regional authorities have been working to supply assistance to the victims and their households, and to guarantee a detailed examination into the occurrence.

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

Despite initial success, subsequent efforts to present the exact same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on occasions that occurred in Zhuhai on November 11, 2024".

The transformed response likewise raised questions about its consistency and reliability.

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

WHICH IS MORE CREATIVE?

Users have praised the ability of Chinese AI apps to deliver structured and even "mentally 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 constructs gradually from curiosity to urgency, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more considerable twist".

"DeepSeek composed a good story however lacked tension and an impactful climax, making Qwen2.5 the apparent option."

Opinions, however, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can also see that it is refraining from doing as highly as others in imaginative writing," he told 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 shocks worldwide 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 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 set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

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

It also brilliantly reimagined conventional 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 Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up an excellent battle, coming up with an equally remarkable cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring 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 myths."

Disappointingly, Qwen2.5 fell short in this difficulty - providing a storyline that appeared more matched for an animation movie.

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

Realising his brand-new reality and "looking for to understand his purpose in this weird new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a quest, 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 conclusive declaration" about which bot was best, including that each showed its own strengths in various areas, "such as language focus, training information and hardware optimization".

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

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate actions to questions about Chinese current occasions, which gives it an included advantage.

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

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

"When given a choice, Chinese users desire the non-censored version - similar to anybody 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 percent of individuals using the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other productive ways," Chen said.