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 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'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically important" and its venture 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 sped up after ChatGPT removed in 2022 and showed pledges of real-world organization applications, Chen told CNA.

But it was DeepSeek's increase that actually "encouraged" the idea that smaller players like start-up companies might have functions to play in AI research and advancements, he includes.

'A lot is up in the air': Is Chinese company DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business just altered the guidelines of tech-geopolitics

The "focus on cost benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning costs - the expenses of utilizing a trained design to reason from brand-new information.

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

"We could see some AI firms focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and incorporate them with clinical research," Chen included.

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

Chinese AI companies are moving rapidly, experts say, developing on DeepSeek's momentum to come up with their own ingenious and affordable methods to apply generative AI to jobs and establish more sophisticated items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential obstacle for Chinese developers, kept in mind Dr Marina Zhang, pipewiki.org an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the capability of Chinese tech business ... forcing numerous to depend on older or lower-performance options which can slow training and lower design abilities," she said.

"While some companies like DeepSeek, have actually discovered innovative ways to enhance or use more standard hardware efficiently, obtaining advanced chips still makes a big difference for training huge AI models."

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

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

Tests recommend Chinese chatbots are set to avoid domestic politics.

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

To further test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "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 heavily censored on Chinese social networks - with just divulging the death toll a day later.

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

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

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

"Its strong concentrate on Chinese-language information may likewise limit its adaptability (to perform) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been evaluated as broadly or on the exact same scale as more established AI models which poses extra obstacles during real-world implementation."

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

That was after several duplicated attempts - 4 triggers to be accurate - in a span of around 20 minutes.

It eventually passed on details about the attack which eliminated 35 people and left dozens of others hurt, likewise going on to note 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 carrying out a thorough examination into the motives and circumstances surrounding the occurrence", details which is now dated.

The driver, Fan, was carried out last month.

This is Qwen2.5's action completely:

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

Date and Time: The incident happened on November 11, disgaeawiki.info 2024, at approximately 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The attack led to 35 deaths and hb9lc.org 43 injuries.

Perpetrator: The driver, determined as Fan Weiqiu (male, 62 years old), was apprehended by the authorities.

Response: The cops responded rapidly to the scene, and emergency situation services worked to carry the hurt to hospitals for treatment.

Investigation: The police are performing an extensive investigation into the intentions and situations surrounding the incident.

This event was widely reported in the media and triggered considerable public issue. The federal government and regional authorities have been working to supply support to the victims and their households, and to guarantee a detailed examination into the event.

If you need more detailed details or have particular questions about the occurrence, yewiki.org do not hesitate to ask.

Despite preliminary success, subsequent efforts to posture the very 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 altered action also raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had been widely published in worldwide news reports at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided a story with a more introspective tone and smoother emotional shifts for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that builds slowly from curiosity to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".

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

Opinions, though, differ.

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

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

As reporters and authors, 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, including main characters from the timeless Chinese folklore impressive, Journey to the West.

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

It included fancy settings - smoggy skies "pierced by skyscrapers", "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 "an ironical, self-aware AI housed in a stolen battle 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 good fight, coming up with an equally dramatic cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching 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 obstacle - providing a story that seemed more suited for an animation film.

"The film begins 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 function in this strange new world", he then escapes 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 safeguard the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "tough to make a definitive declaration" about which bot was best, including that each displayed its own strengths in different locations, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not merely replicating Western paradigms, however rather progressing in affordable innovation methods - 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 movie plot showed its creative flair that made for a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual actions to concerns about Chinese current events, which gives it an included benefit.

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 company Strategy Risks.

"When provided an option, Chinese users want the non-censored variation - much like anybody else, so I feel like that's a piece missing out on from it."

Independent Beijing-based specialist Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly for 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 means," Chen said.