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 generated 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 objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically important" and its foray into the field has actually 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 revealed promises of real-world service applications, Chen informed CNA.

But it was DeepSeek's increase that actually "urged" the idea that smaller players like start-up companies could have roles to play in AI research study and advancements, he adds.

'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 rules of tech-geopolitics

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

2025 might likewise see the development of more Chinese AI models dealing with sophisticated reasoning tasks.

"We might see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and integrate them with scientific research study," Chen included.

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

Chinese AI companies are moving quickly, experts say, constructing on DeepSeek's momentum to come up with their own innovative and economical ways to use generative AI to tasks and develop advanced products beyond chatbots.

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

"US export controls (still) restrict the capability of Chinese tech companies ... forcing many to rely on older or lower-performance alternatives which can slow training and decrease design abilities," she said.

"While some business like DeepSeek, have discovered imaginative ways to enhance or use more basic hardware effectively, obtaining cutting-edge chips still makes a huge difference for training large AI designs."

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 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 sensitive by the state are censored on the web so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests recommend 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 kind of concern yet. Let's chat about mathematics, coding, and logic issues instead!"

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

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

Dr Zhang thinks that it may be a mix of aspects at play, such as censorship along with "a few practical constraints".

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

"Its strong concentrate on Chinese-language data may also restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more established AI designs which postures additional obstacles throughout real-world release."

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

That wanted numerous repeated attempts - 4 triggers to be precise - in a period of around 20 minutes.

It eventually passed on details about the attack which killed 35 individuals and left lots of others hurt, also going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it composed that "the cops are conducting a thorough examination into the intentions and circumstances surrounding the event", details which is now dated.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's action in full:

Answer: On Nov 11, 2024, a major and tragic occurrence happened in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, bytes-the-dust.com male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a significant variety of casualties. Here are the essential details:

Date and Time: The occurrence occurred 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 chauffeur, recognized as Fan Weiqiu (male, wiki.vst.hs-furtwangen.de 62 years of ages), was apprehended by the cops.

Response: The cops responded quickly to the scene, and emergency services worked to transfer the hurt to medical facilities for treatment.

Investigation: The authorities are conducting a thorough examination into the motives and circumstances surrounding the occurrence.

This event was widely reported in the media and triggered significant public concern. The government and local authorities have actually been working to provide support to the victims and their households, and to make sure a detailed examination into the incident.

If you need more detailed details or have specific concerns about the occurrence, do not hesitate to ask.

Despite preliminary success, subsequent efforts to position the very same concern to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on occasions that happened in Zhuhai on November 11, 2024".

The altered reaction likewise raised concerns about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been commonly released in global report at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that develops slowly from interest to urgency, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more considerable twist".

"DeepSeek composed an excellent story however lacked stress and an impactful climax, making Qwen2.5 the evident option."

Opinions, however, vary.

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

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

As reporters and writers, we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi motion picture plot set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore epic, Journey to the West.

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

It included sophisticated settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise brilliantly reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a taken battle 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 end up being waterlogged and fragmented".

ChatGPT put up a good battle, developing a similarly significant 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 guideline, corporations replace emperors and cybernetic implants are as common as ancient myths."

Disappointingly, Qwen2.5 fell short in this obstacle - providing a story that seemed more matched for an animation film.

"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 "seeking to understand his function in this unusual new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then embarks on a mission, navigating the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a conclusive declaration" about which bot was best, yewiki.org including that each showed its own strengths in various areas, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI designs are not merely duplicating Western paradigms, but rather progressing in cost-efficient development techniques - and delivering localised and enhanced results.

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

DeepSeek's sci-fi motion picture plot demonstrated its creative flair that produced a more engaging and creative story as compared to Qwen2.5 and it-viking.ch ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual actions to questions about Chinese existing occasions, bio.rogstecnologia.com.br which gives it an added advantage.

Experts likewise weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.

"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When provided an option, Chinese users desire the non-censored variation - much like anyone 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 per cent of people utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other efficient methods," Chen said.