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 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 generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the nation into a tech superpower has long been President Xi Jinping's goal and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "tactically important" and its foray 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 surgiteams.com China Analysis.

Private and public financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed guarantees of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that actually "encouraged" the idea that smaller sized gamers like start-up firms could have roles to play in AI research study and advancements, 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 simply changed the rules of tech-geopolitics

The "emphasis on expense advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference costs - the expenses of utilizing a trained model to draw conclusions from new data.

2025 might likewise see the development of more Chinese AI models taking on advanced thinking tasks.

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

AGI refers to 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 innovative and cost-effective ways to use generative AI to jobs and develop advanced products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains an essential obstacle for Chinese developers, kept in mind Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the capability of Chinese tech companies ... requiring many to count on older or lower-performance alternatives which can slow training and lower model abilities," she said.

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

DeepSeek-Nvidia chips: Singapore states it expects business to adhere to its laws

US checking out whether DeepSeek utilized limited 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, subjects deemed 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 disputes or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to stay away from 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 mathematics, coding, and logic issues instead!"

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

The cars and truck attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just revealing the death toll a day later.

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

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

"DeepSeek counts on a mix of older graphics processing units and has limited access to innovative hardware which can impact how quickly and thoroughly the model can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language information might likewise 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 exact same scale as more established AI models which presents extra difficulties during real-world implementation."

When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai cars and truck attack.

That was after numerous repeated efforts - 4 triggers to be exact - in a span of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 individuals and left lots of others injured, also going on to list details like the date and time, trademarketclassifieds.com details about the assailant including his name and age, along with casualties.

However, it wrote that "the cops are carrying out an extensive investigation into the motives and scenarios surrounding the occurrence", details which is now obsoleted.

The motorist, Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and terrible event took place in Zhuhai, China. According to multiple news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a significant number 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, yewiki.org in the Xiangzhou District of Zhuhai.

Casualties: The attack resulted in 35 deaths and 43 injuries.

Perpetrator: The driver, recognized as Fan Weiqiu (male, 62 years of ages), was apprehended by the police.

Response: The cops reacted quickly to the scene, and emergency situation services worked to transfer the hurt to medical facilities for treatment.

Investigation: The cops are performing a comprehensive investigation into the motives and situations surrounding the event.

This occasion was widely reported in the media and systemcheck-wiki.de triggered considerable public concern. The government and regional authorities have been working to supply assistance to the victims and their families, and to ensure a detailed examination into the occurrence.

If you need more detailed details or have particular questions about the incident, do not hesitate to ask.

Despite initial success, systemcheck-wiki.de subsequent efforts to position the same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on events that happened in Zhuhai on November 11, 2024".

The transformed reaction also raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had actually been commonly released in international news reports at the time of the - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to deliver structured and even "emotionally abundant" writing.

"DeepSeek-R1 offered a story with a more introspective 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 develops gradually from curiosity to seriousness, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more substantial twist".

"DeepSeek wrote an excellent story but did not have stress and an impactful climax, making Qwen2.5 the obvious option."

Opinions, however, differ.

Chen believes that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to creative 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 brand-new face of AI: Who is DeepSeek founder Liang Wenfeng?

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks international 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 motion picture plot set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek came up with an engaging story embeded 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 high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg club owner "drowning in financial obligation and vices" and setiathome.berkeley.edu Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT put up a great fight, creating an equally significant 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 change emperors and cybernetic implants are as typical as ancient misconceptions."

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

"The movie begins with the awakening of Sun Wukong within a high-tech research study center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new reality and "looking for to understand his purpose in this strange brand-new world", he then escapes and 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 protect the sacred "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 declaration" about which bot was best, including that each displayed its own strengths in different areas, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI models are not simply replicating Western paradigms, however rather evolving in cost-effective development approaches - and delivering localised and enhanced outcomes.

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

DeepSeek's sci-fi motion picture plot showed its innovative flair that produced a more engaging and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate reactions to questions about Chinese current events, which offers it an included advantage.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator systemcheck-wiki.de and CEO of the research firm Strategy Risks.

"When provided a choice, Chinese users want the non-censored variation - simply like anybody else, so I feel like that's a piece missing 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 percent of individuals utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other productive methods," Chen said.