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 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 ending up being the world leader in AI by 2030.

China views AI as being "tactically essential" and its foray into the field has 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 investments in Chinese AI sped up after ChatGPT removed in 2022 and showed pledges of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that really "urged" the concept that smaller sized gamers like start-up companies might have roles to play in AI research and developments, 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 just changed the rules of tech-geopolitics

The "focus on expense advantage" is a distinct function of Chinese AI, Chen states, with lower training and inference costs - the expenses of utilizing a trained model to reason from brand-new data.

2025 could also see the development of more Chinese AI models dealing with innovative reasoning tasks.

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

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

Chinese AI business are moving quickly, analysts say, constructing on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative AI to tasks and develop advanced products beyond chatbots.

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

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

"While some business like DeepSeek, have actually discovered innovative methods to optimize or utilize more standard hardware efficiently, obtaining advanced chips still makes a huge distinction for training very large AI models."

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

US looking into whether DeepSeek used restricted AI chips obtained through other countries, source says

So how do Chinese AI bots compare against ChatGPT? We put them to the test.

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, yewiki.org subjects considered delicate by the state are censored on the web so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what happened 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 math, coding, and logic problems instead!"

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

The car attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities only divulging the death toll a day later on.

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

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

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

"Its strong concentrate on Chinese-language data may also restrict its flexibility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been tested as broadly or on the same scale as more established 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 - four 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 lots of others injured, also 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 wrote that "the police are carrying out an extensive investigation into the intentions and circumstances surrounding the incident", details which is now obsoleted.

The driver, Fan, was carried out last month.

This is Qwen2.5's response completely:

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

Date and Time: The event took place 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 driver, recognized as Fan Weiqiu (male, surgiteams.com 62 years old), was nabbed by the police.

Response: The police reacted quickly to the scene, trademarketclassifieds.com and emergency situation services worked to transfer the injured to hospitals for treatment.

Investigation: The authorities are carrying out an extensive examination into the motives and scenarios surrounding the incident.

This occasion was commonly reported in the media and caused significant public concern. The government and regional authorities have actually been working to provide assistance to the victims and their households, and to ensure a detailed investigation into the incident.

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

Despite preliminary success, subsequent efforts to position the exact same question 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 transformed response also raised concerns about its consistency and dependability.

Predictably, ChatGPT cited public details that had actually been commonly released in worldwide news reports at the time of the accident - 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 reflective tone and smoother psychological transitions for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that constructs gradually from curiosity to urgency, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek wrote a great story however lacked stress and an impactful climax, making Qwen2.5 the evident choice."

Opinions, though, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as strongly as others in imaginative writing," he informed CNA.

Related:

China's new face of AI: Who is DeepSeek creator Liang Wenfeng?

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks international AI scene

As reporters and writers, we needed 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, featuring main characters from the classic Chinese folklore impressive, Journey to the West.

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

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

It also remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT set up a good fight, developing a similarly dramatic cyberpunk storyline 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 rule, corporations replace emperors and cybernetic implants are as typical as ancient myths."

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

"The movie starts with the awakening of Sun Wukong within a state-of-the-art research study facility located in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "looking for to comprehend his function in this weird brand-new world", he then leaves and pediascape.science meets Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not merely duplicating Western paradigms, however rather evolving in cost-effective development approaches - and delivering localised and improved outcomes.

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

DeepSeek's sci-fi film plot showed its innovative flair that made for a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate reactions to questions about Chinese existing events, which gives it an added benefit.

Experts likewise weighed in on their thoughts 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 study company Strategy Risks.

"When offered a choice, Chinese users desire the non-censored variation - much like anyone 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 using the tool are not attempting to get a deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other productive methods," Chen said.