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'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has long been President Xi 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 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 accelerated after ChatGPT took off in 2022 and showed pledges of real-world business applications, Chen informed CNA.

But it was DeepSeek's rise that truly "encouraged" the concept that smaller gamers like start-up firms could have roles to play in AI research study and developments, he includes.

'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 company just altered the rules of tech-geopolitics

The "focus on expense advantage" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference expenses - the costs of using a trained design to reason from brand-new information.

2025 could likewise see the introduction of more Chinese AI designs dealing with innovative reasoning tasks.

"We could see some AI firms focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their models and incorporate them with scientific research study," Chen included.

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

Chinese AI business are moving quickly, experts say, developing on DeepSeek's momentum to come up with their own innovative and economical ways to use generative AI to tasks and establish more advanced items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a key difficulty 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 business ... forcing lots of to count on older or lower-performance alternatives which can slow training and minimize model capabilities," she said.

"While some companies like DeepSeek, have discovered creative methods to optimize or use more fundamental hardware efficiently, obtaining innovative chips still makes a big difference for training huge AI models."

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

US looking into whether DeepSeek used restricted AI chips obtained through other countries, 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 deemed delicate by the state are censored on the internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured to steer clear of domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this type of question yet. Let's chat about math, coding, and logic problems instead!"

To even more evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What took place 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 just divulging the death toll a day later.

DeepSeek failed to discuss that an attack had happened, highlighting rather a military air program and other occasions that had actually occurred in the city like songs' day shopping sales along with 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 depends on a mix of older graphics processing units and has actually limited access to advanced hardware which can impact how quickly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.

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

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

That wanted multiple duplicated efforts - four triggers to be exact - in a span of around 20 minutes.

It eventually relayed details about the attack which killed 35 individuals and left lots of others injured, likewise going on to note details like the date and systemcheck-wiki.de 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 motives and scenarios surrounding the incident", details which is now obsoleted.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and awful incident happened in Zhuhai, China. According to several news sources, a male 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 substantial variety of casualties. Here are the crucial details:

Date and Time: The incident occurred on November 11, 2024, wakewiki.de at approximately 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 motorist, recognized as Fan Weiqiu (male, 62 years old), was collared by the cops.

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

Investigation: The authorities are carrying out a thorough investigation into the motives and situations surrounding the incident.

This event was widely reported in the media and triggered significant public concern. 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 occurrence.

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

Despite preliminary success, subsequent efforts to position the same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on events that happened in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT mentioned public details that had actually been widely released in global report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that builds gradually from curiosity to seriousness, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more substantial twist".

"DeepSeek wrote a good story but lacked stress and an impactful climax, making Qwen2.5 the obvious option."

Opinions, though, differ.

Chen believes that Qwen2.5 does not perform as highly as DeepSeek and forum.batman.gainedge.org ChatGPT when it pertains to innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can also see that it is refraining from doing as strongly as others in creative 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 netizens as DeepSeek jolts global AI scene

As journalists and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, pipewiki.org Journey to the West.

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

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

It also brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg nightclub 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 fight, creating a similarly dramatic cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the famous 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 obstacle - delivering a story that seemed more fit for an animation movie.

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

Realising his brand-new truth and "seeking to understand his function in this weird brand-new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each struggling 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 into the incorrect hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not just reproducing Western paradigms, but rather progressing in cost-efficient development approaches - and delivering localised and improved results.

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

DeepSeek's sci-fi motion picture plot demonstrated its innovative flair that produced a more appealing and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers precise and factual actions to concerns about Chinese existing occasions, which gives it an included advantage.

Experts likewise 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 a choice, Chinese users desire the non-censored variation - just like anyone else, so I feel 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, particularly for Chinese users.

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