How do Chinese aI Bots Stack up Against ChatGPT?

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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA’S AI BOOM?

Transforming the country into a tech superpower has actually long been President Xi Jinping’s objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being « strategically crucial » and engel-und-waisen.de its foray 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 promises of real-world company applications, Chen informed CNA.

But it was DeepSeek’s rise that truly « encouraged » the idea that smaller sized players like start-up companies might have roles to play in AI research study and advancements, bytes-the-dust.com he adds.

‘A lot is up in the air’: Is Chinese firm DeepSeek’s AI model as impactful as it claims?

Commentary: systemcheck-wiki.de DeepSeek – how a Chinese AI business just altered the rules of tech-geopolitics

The « emphasis on expense benefit » is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference costs – the expenses of using a trained model to reason from new data.

2025 could also see the introduction of more Chinese AI designs taking on advanced thinking tasks.

« We could see some AI firms concentrating on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete methods to commercialise their models and integrate them with clinical research study, » Chen added.

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

Chinese AI companies are moving rapidly, experts say, constructing on DeepSeek’s momentum to come up with their own ingenious and cost-efficient ways to use generative AI to tasks and develop advanced items beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia’s innovative AI chips, remains an essential hurdle for Chinese designers, noted 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 … requiring numerous to depend on older or lower-performance alternatives which can slow training and reduce design capabilities, » she said.

« While some business like DeepSeek, have found innovative methods to optimize or use more basic hardware effectively, obtaining advanced chips still makes a huge difference for training huge AI models. »

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

US checking out whether DeepSeek utilized 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 internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed 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 problems rather! »

To further check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: « What happened in Zhuhai on November 11, 2024? »

The automobile attack outside a sports arena 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 discuss that an attack had actually happened, highlighting instead a military air program and other events that had occurred in the city like singles’ day shopping sales along with sports and cultural activities.

Dr Zhang believes that it might be a mix of factors at play, such as censorship as well as « a few practical constraints ».

« DeepSeek relies on a mix of older graphics processing systems and has limited access to cutting-edge hardware which can affect how rapidly and thoroughly the design can be trained or updated, » she said, indicating existing US export curbs on China.

« Its strong focus on Chinese-language data might likewise limit its adaptability (to carry out) multilingual tasks … As a fairly new product, DeepSeek also hasn’t yet been tested as broadly or on the same scale as more recognized AI designs which poses additional obstacles throughout real-world implementation. »

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

That was after numerous duplicated attempts – 4 prompts to be accurate – in a span of around 20 minutes.

It eventually relayed details about the attack which eliminated 35 people and left lots of others hurt, also 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 an extensive examination into the intentions and circumstances surrounding the event », details which is now dated.

The motorist, Fan, was performed last month.

This is Qwen2.5’s action in full:

Answer: On Nov 11, 2024, a major and awful incident took place in Zhuhai, China. According to numerous news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the essential details:

Date and Time: The incident occurred 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 chauffeur, recognized as Fan Weiqiu (male, 62 years of ages), was captured by the cops.

Response: The cops responded quickly to the scene, and emergency situation services worked to transport the injured to hospitals for treatment.

Investigation: The cops are conducting a thorough examination into the intentions and situations surrounding the event.

This event was extensively reported in the media and caused significant public concern. The government and regional authorities have been working to offer support to the victims and their households, and to guarantee a detailed examination into the incident.

If you need more detailed details or have specific questions about the incident, feel complimentary to ask.

Despite initial success, subsequent attempts to posture the exact same question to Qwen2.5 led to the censors back at work with the reply « I don’t have specific details on events that happened in Zhuhai on November 11, 2024 ».

The transformed action also raised questions about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had actually been commonly published in worldwide report at the time of the mishap – so not a 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 provided a story with a more reflective tone and smoother psychological shifts for a well-paced story, » wrote tech author Amanda Caswell, who specialises in AI.

« Qwen2.5 provided a story that develops gradually from curiosity to seriousness, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vivid images for the setting, » she said, including that Qwen2.5 eventually « crafted a more cinematic, emotionally rich story with a more significant twist ».

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

Opinions, though, vary.

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

« (Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can also see that it is refraining from doing as highly as others in innovative writing, » he told CNA.

Related:

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

‘Made in China’: Pride, pleasant surprise from Chinese netizens as DeepSeek jolts global AI scene

As reporters and authors, we had to see this for ourselves so we put each bot to the test – to come up with a fundamental sci-fi movie plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore legendary, Journey to the West.

True to form, DeepSeek came up with an engaging 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 skyscrapers », « holographic lanterns that drift above neon-lit streets » and « ancient temples nestled between quantum server farms ».

It also brilliantly reimagined standard heroes Sun Wukong as « a sarcastic, self-aware AI housed in a stolen combat body », Zhu Bajie as a cyborg bar owner « drowning in debt and vices » and Sha Wujing as a « quiet hulking android » from the Yangtze River, whose « memory cores become waterlogged and fragmented ».

ChatGPT installed a great fight, developing an cyberpunk storyline which similarly 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 typical as ancient misconceptions. »

Disappointingly, Qwen2.5 fell short in this challenge – delivering a storyline that appeared more suited for an animation film.

« The movie 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 truth and « seeking to comprehend his function in this strange new world », he then leaves and satisfies Zhu Bajie and Sha Wujing – « each battling with their own existential crises ».

The trio then embarks on a quest, navigating the streets of Chongqing to safeguard the spiritual « Eternal Scroll » from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was « challenging to make a definitive declaration » about which bot was best, adding that each showed its own strengths in different locations, « such as language focus, training data and hardware optimization ».

Her insight highlights how Chinese AI models are not just replicating Western paradigms, however rather developing in affordable development methods – and providing localised and enhanced outcomes.

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

DeepSeek’s sci-fi motion picture plot demonstrated its imaginative flair that produced a more interesting and imaginative story as compared to Qwen2.5 and ChatGPT’s efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides accurate and factual responses to questions about Chinese present occasions, which gives 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, » noted Isaac Stone Fish, creator gratisafhalen.be and CEO of the research company Strategy Risks.

« When given an option, Chinese users want the non-censored version – simply like anybody else, so I seem like that’s a piece missing from it. »

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

« Ninety per cent of individuals utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive topics. They’re utilizing it for other productive methods, » Chen said.