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 generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags 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 "tactically essential" 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 sped up after ChatGPT took off in 2022 and showed guarantees of real-world service applications, links.gtanet.com.br Chen informed CNA.

But it was DeepSeek's rise that actually "urged" the idea that smaller sized players like start-up firms could have roles 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 business simply changed the guidelines of tech-geopolitics

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

2025 could also see the emergence of more Chinese AI models taking on sophisticated thinking jobs.

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

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

Chinese AI business are moving quickly, experts state, building on DeepSeek's momentum to come up with their own ingenious and wiki.dulovic.tech economical ways to apply generative AI to tasks and wiki.whenparked.com develop more innovative items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains an essential difficulty 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 capability of Chinese tech business ... forcing lots of to rely on older or lower-performance alternatives which can slow training and lower design abilities," she said.

"While some business like DeepSeek, have actually discovered imaginative methods to enhance or use more fundamental hardware efficiently, obtaining cutting-edge chips still makes a big distinction for training large AI models."

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

US checking out whether DeepSeek used restricted AI chips obtained through other nations, 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, topics considered sensitive by the state are censored on the web so it should come as no 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 configured to stay away from 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 mathematics, coding, and logic problems instead!"

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

The car attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities only revealing the death toll a day later on.

DeepSeek failed to point out that an attack had actually occurred, highlighting rather a military air program and other events that had actually occurred in the city like singles' day shopping sales as well as sports and cultural activities.

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

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

"Its strong focus on Chinese-language data may also restrict its versatility (to perform) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the same scale as more recognized AI designs which postures extra difficulties during real-world release."

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

That wanted numerous duplicated efforts - four prompts to be accurate - in a period of around 20 minutes.

It eventually communicated details about the attack which killed 35 individuals and left lots of others hurt, likewise 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 composed that "the authorities are conducting an extensive investigation into the motives and scenarios surrounding the occurrence", details which is now outdated.

The motorist, Fan, was performed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and terrible incident occurred in Zhuhai, China. According to several 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, leading to a substantial variety of casualties. Here are the key details:

Date and Time: hb9lc.org The occurrence took place 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 driver, identified as Fan Weiqiu (male, 62 years of ages), was apprehended by the authorities.

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

Investigation: The authorities are carrying out a comprehensive investigation into the intentions and wiki.myamens.com situations surrounding the occurrence.

This occasion was widely reported in the media and triggered significant public concern. The federal government and regional authorities have actually been working to provide support to the victims and their households, and to make sure a detailed investigation into the occurrence.

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

Despite initial success, subsequent efforts to pose the same concern to Qwen2.5 led to the censors back at work with the reply "I don't have particular details on events that happened in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT mentioned public details that had actually been extensively published in global report at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided 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 builds slowly from interest to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more considerable twist".

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

Opinions, though, 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 tasks, however we can also see that it is refraining from doing as strongly as others in innovative writing," he informed CNA.

Related:

China's brand-new face of AI: Who is DeepSeek founder Liang Wenfeng?

'Made in China': Pride, enjoyable 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, featuring main characters from the traditional Chinese folklore impressive, Journey to the West.

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

It included 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 standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg club owner "drowning in debt 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 battle, creating an equally significant cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities guideline, corporations change emperors and cybernetic implants are as common as ancient myths."

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

"The film starts with the awakening of Sun Wukong within a state-of-the-art research facility situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "seeking to comprehend his function in this weird brand-new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not merely replicating Western paradigms, however rather developing in cost-efficient innovation approaches - and delivering localised and enhanced results.

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

DeepSeek's sci-fi film plot demonstrated its innovative flair that produced a more appealing and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, archmageriseswiki.com supplies precise and accurate responses to concerns about Chinese existing occasions, which provides it an added advantage.

Experts also weighed in on their thoughts 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 firm Strategy Risks.

"When offered an option, Chinese users want the non-censored variation - much like 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 attempting to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other efficient methods," Chen said.