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 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 essential" and its venture into the field has actually been "years in the making", said Chen Qiheng, an affiliated researcher 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 guarantees of real-world business applications, Chen informed CNA.

But it was DeepSeek's increase that actually "urged" the concept that smaller sized players like could have roles to play in AI research study and advancements, he includes.

'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 rules of tech-geopolitics

The "focus on expense advantage" is a distinctive feature of Chinese AI, Chen states, with lower training and inference costs - the expenses of using a trained model to draw conclusions from new information.

2025 might also see the development of more Chinese AI designs taking on advanced thinking jobs.

"We might see some AI companies concentrating on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and incorporate them with scientific research," Chen added.

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

Chinese AI business are moving quickly, experts say, developing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to use generative AI to tasks and establish advanced products beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a key difficulty for Chinese designers, 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 business ... requiring lots of to depend on older or lower-performance alternatives which can slow training and lower design capabilities," she said.

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

DeepSeek-Nvidia chips: Singapore states it anticipates business to adhere to its laws

US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, source states

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, subjects deemed sensitive by the state are censored on the web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell 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 kind of question yet. Let's chat about mathematics, coding, and logic problems instead!"

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

The cars and truck attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities just divulging the death toll a day later.

DeepSeek failed to point out that an attack had actually occurred, highlighting instead a military air program and other events that had happened in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it may be a mix of elements at play, such as censorship as well as "a few useful constraints".

"DeepSeek counts on a mix of older graphics processing systems and has actually limited access to innovative hardware which can impact how rapidly and extensively the model can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language data might likewise restrict its versatility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the very same scale as more established AI models which postures additional obstacles during real-world implementation."

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

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

It ultimately passed on details about the attack which killed 35 individuals and left lots of others injured, also going on to list details like the date and time, details about the assailant including his name and age, along with casualties.

However, it wrote that "the cops are conducting a comprehensive investigation into the motives and scenarios surrounding the occurrence", details which is now outdated.

The driver, Fan, was carried out last month.

This is Qwen2.5's response in full:

Answer: On Nov 11, 2024, a significant and terrible incident happened in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the essential details:

Date and Time: The incident occurred on November 11, 2024, at around 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 chauffeur, identified as Fan Weiqiu (male, 62 years old), was captured by the authorities.

Response: The cops responded rapidly to the scene, and emergency situation services worked to carry the injured to health centers for treatment.

Investigation: The police are conducting an extensive examination into the motives and scenarios surrounding the incident.

This event was commonly reported in the media and caused considerable public concern. The federal government and regional authorities have been working to supply assistance to the victims and their households, and to guarantee a detailed examination into the incident.

If you need more detailed details or have specific questions about the occurrence, feel complimentary to ask.

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

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

Predictably, ChatGPT cited public details that had actually been widely published in global news reports at the time of the mishap - 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 introspective tone and smoother emotional shifts for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that develops gradually from interest to urgency, keeping the reader engaged. It offers an unexpected 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 substantial twist".

"DeepSeek wrote an excellent story however did not have stress and an impactful climax, making Qwen2.5 the apparent option."

Opinions, however, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can also see that it is refraining from doing as strongly as others in creative writing," he informed 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 jolts global AI scene

As journalists and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi film plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore impressive, 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 included 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 "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed a great battle, creating an equally remarkable cyberpunk story which likewise 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 change emperors and cybernetic implants are as typical as ancient misconceptions."

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

"The motion picture begins with the awakening of Sun Wukong within a state-of-the-art research center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "seeking to understand his purpose in this weird brand-new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then embarks on 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 kept in mind that it was "difficult to make a conclusive 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 underscores how Chinese AI models are not just duplicating Western paradigms, but rather progressing in economical innovation methods - and delivering localised and enhanced results.

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 produced a more appealing and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual reactions to concerns about Chinese existing events, which offers it an included advantage.

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

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

"When given a choice, Chinese users want the non-censored variation - just like anyone else, so I feel like that's a piece missing out on from it."

Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for garagesale.es Chinese users.

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