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 startup 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 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 engel-und-waisen.de its venture 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 investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed pledges of real-world business applications, Chen informed CNA.

But it was DeepSeek's rise that really "urged" the idea that smaller players like start-up firms might have functions to play in AI research and advancements, he adds.

'A lot is up in the air': Is Chinese firm DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business just changed the guidelines of tech-geopolitics

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

2025 could also see the introduction of more Chinese AI designs dealing with innovative thinking tasks.

"We might see some AI firms focusing on getting closer to artificial basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with clinical research study," Chen added.

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

Chinese AI business are moving rapidly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and affordable methods to use generative AI to jobs and establish more sophisticated products beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential obstacle 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) limit the capability of Chinese tech companies ... requiring lots of to count on older or lower-performance alternatives which can slow training and decrease design capabilities," she said.

"While some companies like DeepSeek, have actually discovered creative methods to optimize or utilize more basic hardware effectively, obtaining cutting-edge chips still makes a big distinction for training large AI designs."

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

US checking out whether DeepSeek used restricted AI chips obtained through other nations, 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, topics deemed delicate by the state are censored on the internet so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform 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 concern yet. Let's chat about math, coding, and logic problems instead!"

To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What happened in Zhuhai on November 11, 2024?"

The cars and truck attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social networks - with authorities only divulging the death toll a day later on.

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

Dr Zhang believes that it might be a mix of elements at play, such as censorship as well as "a couple of practical constraints".

"DeepSeek depends on a mix of older graphics processing units and has limited access to cutting-edge hardware which can impact how rapidly 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 likewise limit its flexibility (to perform) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established AI models which presents additional difficulties throughout real-world implementation."

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

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

It eventually passed on details about the attack which eliminated 35 individuals and left lots of others injured, 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, bytes-the-dust.com it wrote that "the cops are conducting a comprehensive examination into the intentions and circumstances surrounding the event", details which is now dated.

The motorist, Fan, was executed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, yewiki.org 2024, a major and tragic incident took place in Zhuhai, China. According to multiple news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the key details:

Date and Time: The event occurred on November 11, 2024, at roughly 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 motorist, determined as Fan Weiqiu (male, 62 years of ages), was apprehended by the cops.

Response: The cops reacted quickly to the scene, and emergency services worked to transport the injured to medical facilities for treatment.

Investigation: The cops are conducting an extensive examination into the intentions and scenarios surrounding the incident.

This occasion was widely reported in the media and caused significant public concern. The government and local authorities have been working to supply assistance to the victims and their families, and to guarantee a detailed examination into the occurrence.

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

Despite initial success, subsequent attempts to pose the same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on occasions that occurred in Zhuhai on November 11, 2024".

The altered response also raised concerns about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had been extensively released in worldwide report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that constructs gradually from curiosity to urgency, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more significant twist".

"DeepSeek composed an excellent story but did not have tension and an impactful climax, making Qwen2.5 the apparent option."

Opinions, though, vary.

Chen believes that Qwen2.5 does not perform 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 likewise see that it is refraining from doing as highly as others in imaginative writing," he told CNA.

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese as DeepSeek jolts global AI scene

As reporters 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 epic, 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 merges with quantum computing".

It consisted of fancy settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

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

ChatGPT installed a good battle, developing a similarly remarkable 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 misconceptions."

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

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

Realising his brand-new truth and "looking for to comprehend his purpose in this unusual new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then embarks on a mission, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI designs are not merely duplicating Western paradigms, however rather developing in economical development techniques - and providing localised and enhanced results.

In our tests, each bot showcased their own special strengths, forum.pinoo.com.tr which certainly made direct comparisons challenging.

DeepSeek's sci-fi movie plot showed its creative flair that produced a more appealing and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate actions to concerns about Chinese current occasions, which provides it an added advantage.

Experts also weighed in on their thoughts after utilizing 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 provided an option, Chinese users desire the non-censored variation - similar to anyone else, so I feel like that's a piece missing from it."

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

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