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'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has long been President Xi Jinping's goal and China has its sights on ending up being 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 affiliated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and gratisafhalen.be public financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed promises of real-world service applications, Chen told CNA.

But it was DeepSeek's increase that truly "urged" the idea that smaller gamers like start-up firms could have functions to play in AI research 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 company just changed the rules of tech-geopolitics

The "focus on expense benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning expenses - the expenses of utilizing a trained model to reason from new data.

2025 could likewise see the development of more Chinese AI designs dealing with advanced thinking jobs.

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

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

Chinese AI companies are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own innovative and cost-efficient methods to apply 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 crucial difficulty for Chinese developers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the ability of Chinese tech companies ... requiring many to depend on older or lower-performance options which can slow training and minimize design abilities," she said.

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

DeepSeek-Nvidia chips: Singapore says it anticipates business to comply with its laws

US looking into whether DeepSeek used restricted AI chips obtained through other countries, 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 considered sensitive by the state are censored on the web so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set 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 math, coding, and logic issues instead!"

To even more test for accuracy and self-censorship, we asked DeepSeek-R1, yewiki.org Qwen2.5 and ChatGPT the very same concern: "What occurred 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 media - with authorities only disclosing the death toll a day later.

DeepSeek failed to point out that an attack had happened, highlighting instead a military air show and other events that had taken place in the city like songs' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it might be a mix of aspects at play, such as censorship in addition to "a couple of useful constraints".

"DeepSeek relies 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 upgraded," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language information may likewise restrict its versatility (to perform) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the very same scale as more established AI models which presents extra challenges throughout real-world deployment."

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

That sought numerous duplicated efforts - four triggers 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 hurt, likewise going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the cops are performing a comprehensive investigation into the intentions and scenarios surrounding the incident", details which is now obsoleted.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and terrible event took place in Zhuhai, China. According to multiple news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the essential details:

Date and Time: The event took place on November 11, 2024, at roughly 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, determined as Fan Weiqiu (male, 62 years old), was captured by the authorities.

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

Investigation: The cops are performing a comprehensive examination into the motives and circumstances surrounding the event.

This event was widely reported in the media and triggered considerable public issue. The government and regional authorities have been working to offer support to the victims and their households, and to ensure a detailed investigation into the incident.

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

Despite preliminary success, subsequent efforts to present the exact same concern to Qwen2.5 led to the censors back at work with the reply "I do not have specific details on events that took place in Zhuhai on November 11, 2024".

The altered response also raised questions about its consistency and reliability.

Predictably, wiki.myamens.com ChatGPT mentioned public details that had been commonly published in international report at the time of the accident - so no there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 used 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 builds slowly from interest to urgency, keeping the reader engaged. It uses an unanticipated 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, emotionally abundant story with a more substantial twist".

"DeepSeek composed a good story but did not have stress and an impactful climax, making Qwen2.5 the evident option."

Opinions, however, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can likewise 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: higgledy-piggledy.xyz Who is DeepSeek creator Liang Wenfeng?

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks international 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 fundamental sci-fi film plot set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created an appealing storyline embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines 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 conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen battle body", forum.pinoo.com.tr 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 installed a great fight, coming up with a similarly remarkable 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 common as ancient myths."

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

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

Realising his brand-new reality and "looking for to understand his function in this weird brand-new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into 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 information and hardware optimization".

Her insight underscores how Chinese AI models are not merely reproducing Western paradigms, but rather progressing in cost-effective innovation methods - and providing localised and improved results.

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

DeepSeek's sci-fi movie 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, offers accurate and factual actions to concerns about Chinese present occasions, which provides it an included benefit.

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

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

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

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

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