eleeo-europe

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 start-up DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is created 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 goal and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically essential" and its venture into the field has 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 removed in 2022 and revealed pledges of real-world business applications, Chen informed CNA.

But it was DeepSeek's increase that really "encouraged" the concept that smaller sized players like start-up companies could have functions to play in AI research study and advancements, he adds.

'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 changed the guidelines of tech-geopolitics

The "emphasis on expense benefit" is a distinct function of Chinese AI, Chen says, with lower training and wiki.vst.hs-furtwangen.de inference costs - the expenses of using a trained design to reason from new information.

2025 might also see the emergence of more Chinese AI designs tackling advanced thinking tasks.

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

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 establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a crucial hurdle for Chinese developers, kept in mind Dr Marina Zhang, surgiteams.com an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the ability of Chinese tech companies ... forcing numerous to depend on older or lower-performance alternatives which can slow training and reduce model capabilities," she said.

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

DeepSeek-Nvidia chips: Singapore states it expects business to comply with 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, topics deemed delicate by the state are censored on the internet so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured 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 issues instead!"

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

The vehicle attack outside a sports arena in the southern Chinese city was censored on Chinese social media - with authorities only divulging the death toll a day later.

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

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

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

"Its strong focus on Chinese-language information might also restrict its versatility (to bring out) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been evaluated as broadly or on the very same scale as more recognized AI models which positions extra challenges throughout real-world release."

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

That sought multiple duplicated efforts - 4 triggers to be exact - in a span of around 20 minutes.

It eventually relayed details about the attack which killed 35 individuals and left dozens of others injured, also 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 wrote that "the authorities are performing a thorough investigation into the intentions and scenarios surrounding the occurrence", details which is now dated.

The chauffeur, raovatonline.org Fan, was carried out last month.

This is Qwen2.5's reaction in full:

Answer: On Nov 11, 2024, a major and tragic occurrence happened in Zhuhai, China. According to numerous news sources, a guy called Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the crucial details:

Date and Time: The incident took place 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 driver, identified as Fan Weiqiu (male, 62 years old), was collared by the police.

Response: The cops responded quickly to the scene, and emergency situation services worked to carry the hurt to healthcare facilities for treatment.

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

This event was widely reported in the media and caused considerable public issue. The federal government and regional authorities have actually been working to offer support to the victims and their families, and to guarantee a detailed investigation into the occurrence.

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

Despite preliminary success, subsequent attempts to position the same question 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 modified reaction also raised questions about its consistency and dependability.

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

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided a story with a more reflective tone and smoother psychological transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds gradually from curiosity to seriousness, keeping the reader engaged. It provides 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 a great 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 creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can also see that it is refraining from doing as highly as others in imaginative 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 worldwide AI scene

As journalists and writers, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi motion picture 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 came up with 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 consisted of sophisticated 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 standard heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg bar 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 a good fight, surgiteams.com coming up with a similarly significant cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".

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

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

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

Realising his brand-new reality and "seeking to understand his purpose in this strange new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling into the incorrect 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 areas, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI models are not just replicating Western paradigms, but rather progressing in cost-efficient innovation methods - and delivering localised and improved results.

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

DeepSeek's sci-fi film plot showed its imaginative flair that produced a more interesting and creative 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 concerns about Chinese existing occasions, which offers it an added advantage.

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

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

"When provided a choice, Chinese users desire the non-censored version - just like anybody else, so I seem 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, particularly for Chinese users.

"Ninety percent of individuals utilizing the tool are not attempting to get a deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other productive ways," Chen said.