GitLab

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, forum.pinoo.com.tr Chinese start-up 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 country into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically important" and 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 investments in Chinese AI sped up after ChatGPT took off in 2022 and showed pledges of real-world service applications, Chen informed CNA.

But it was DeepSeek's rise that actually "encouraged" the idea that smaller sized players like start-up firms might have functions to play in AI research and developments, he includes.

'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 simply altered the guidelines of tech-geopolitics

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

2025 could likewise see the introduction of more Chinese AI models dealing with innovative thinking tasks.

"We could see some AI companies 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 included.

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

Chinese AI companies are moving quickly, analysts state, developing on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to apply generative AI to jobs and establish advanced items beyond chatbots.

But on the flip side, access to high-end hardware, wiki.lafabriquedelalogistique.fr particularly Nvidia's advanced AI chips, remains an essential 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) restrict the ability of Chinese tech business ... requiring numerous to depend on older or lower-performance options which can slow training and decrease model abilities," she said.

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

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

US looking into whether DeepSeek utilized limited AI chips obtained through other nations, bytes-the-dust.com 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, subjects considered delicate by the state are censored on the internet so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what occurred in Tiananmen Square in 1989.

Tests recommend 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 concern yet. Let's chat about math, coding, and logic issues instead!"

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

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

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

Dr Zhang believes that it may be a mix of aspects at play, such as censorship in addition to "a few practical constraints".

"DeepSeek relies on a mix of older graphics processing units and has restricted access to advanced hardware which can impact how quickly and thoroughly the design 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 versatility (to perform) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the very same scale as more recognized AI designs which presents extra difficulties during real-world deployment."

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

That wanted several repeated efforts - four prompts to be exact - in a period of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 people and left dozens of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that "the police are performing an extensive examination into the motives and scenarios surrounding the event", details which is now outdated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a major and terrible incident took place in Zhuhai, China. According to multiple news sources, a man 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 of casualties. Here are the essential details:

Date and Time: The occurrence occurred 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 driver, determined as Fan Weiqiu (male, 62 years of ages), was nabbed by the cops.

Response: The cops reacted rapidly to the scene, and emergency situation services worked to carry the hurt to hospitals for treatment.

Investigation: The cops are conducting a thorough investigation into the intentions and circumstances surrounding the occurrence.

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

If you require more detailed details or have specific questions about the incident, feel totally free to ask.

Despite initial success, subsequent efforts to present the same question to Qwen2.5 led to 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 modified action also raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been widely published in international news reports 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 deliver 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," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that develops slowly from curiosity to seriousness, keeping the reader engaged. It uses 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 substantial twist".

"DeepSeek wrote an excellent story but lacked tension and an impactful climax, making Qwen2.5 the apparent option."

Opinions, though, vary.

Chen believes that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to imaginative 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 innovative writing," he told CNA.

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks worldwide 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 basic sci-fi film 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 story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It consisted of 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 traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle 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 fight, developing an equally remarkable cyberpunk storyline 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 rule, corporations change emperors and cybernetic implants are as common as ancient misconceptions."

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

"The movie starts 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 understand his function in this unusual new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a conclusive declaration" about which bot was best, adding that each showed 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, however rather evolving in affordable development methods - and delivering localised and improved outcomes.

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

DeepSeek's sci-fi movie plot showed its creative 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 accurate and genbecle.com accurate actions to questions about Chinese existing events, which gives it an added benefit.

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

"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research study company Strategy Risks.

"When offered a choice, Chinese users want the non-censored variation - 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, specifically for Chinese users.

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