juxiong

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 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 actually long been President Xi Jinping's goal 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 actually 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 financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed guarantees of real-world company applications, Chen told CNA.

But it was DeepSeek's increase that really "urged" the idea that smaller sized gamers like start-up companies could have roles to play in AI research and developments, 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 simply altered the rules of tech-geopolitics

The "focus on expense benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference costs - the costs of using a trained model to draw conclusions from brand-new information.

2025 could also see the introduction of more Chinese AI models taking on advanced reasoning jobs.

"We might see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with scientific research," Chen included.

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

Chinese AI business are moving quickly, analysts say, constructing on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to use generative AI to jobs and develop more advanced items beyond chatbots.

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

"US export controls (still) restrict the ability of Chinese tech companies ... requiring 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 actually discovered creative ways to enhance or use more standard hardware efficiently, obtaining innovative chips still makes a huge difference for training very big AI designs."

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

US looking into whether DeepSeek used limited AI chips obtained through other nations, source states

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

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, subjects considered sensitive 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 disagreements or inform you what took place in Tiananmen Square in 1989.

Tests suggest 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 question yet. Let's chat about mathematics, coding, and logic issues instead!"

To further test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: "What happened 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 media - with authorities just divulging the death toll a day later on.

DeepSeek failed to discuss that an attack had taken location, highlighting instead a military air show and other events that had taken place in the city like singles' day shopping sales in addition to sports and cultural activities.

Dr Zhang believes that it may be a mix of factors at play, such as censorship as well as "a few practical constraints".

"DeepSeek relies on a mix of older graphics processing units and has actually limited access to innovative hardware which can affect how rapidly and extensively the design can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language information may also limit its adaptability (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek likewise hasn't yet been checked as broadly or on the very same scale as more recognized AI models which postures extra challenges throughout real-world implementation."

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

That was after several duplicated efforts - 4 triggers to be precise - in a span of around 20 minutes.

It eventually passed on details about the attack which killed 35 individuals and left dozens of others hurt, likewise going on to note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it that "the police are carrying out an extensive examination into the motives and circumstances surrounding the occurrence", details which is now outdated.

The motorist, Fan, was performed last month.

This is Qwen2.5's response in complete:

Answer: setiathome.berkeley.edu On Nov 11, 2024, a significant and terrible event happened in Zhuhai, China. According to multiple news sources, a male called Fan Weiqiu (樊某, bytes-the-dust.com 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 occurrence occurred on November 11, 2024, 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, identified as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

Response: The police reacted rapidly to the scene, and emergency situation services worked to carry the hurt to healthcare facilities for treatment.

Investigation: The cops are carrying out a comprehensive examination into the intentions and circumstances surrounding the occurrence.

This occasion was extensively reported in the media and triggered considerable public concern. The federal government and local authorities have been working to offer assistance to the victims and their households, and to make sure a detailed examination into the incident.

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

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

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

Predictably, ChatGPT cited public details that had actually been widely released in worldwide news reports at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that builds gradually from curiosity to urgency, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more substantial twist".

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

Opinions, though, vary.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to innovative writing.

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

Related:

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

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

As journalists and authors, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi motion picture plot set in the futuristic megacity of Chongqing, surgiteams.com featuring main characters from the traditional Chinese folklore impressive, Journey to the West.

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

It included intricate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled 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 become waterlogged and fragmented".

ChatGPT put up an excellent battle, setiathome.berkeley.edu 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 typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this obstacle - providing a story that seemed more suited for an animation movie.

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

Realising his new reality and "looking for to understand his purpose in this odd new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then starts a quest, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not simply duplicating Western paradigms, however rather evolving in economical development techniques - and delivering localised and enhanced results.

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

DeepSeek's sci-fi motion picture plot showed its creative flair that made for a more interesting and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual reactions to questions about Chinese existing events, which gives it an included benefit.

Experts also weighed in on their thoughts 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, founder and CEO of the research company Strategy Risks.

"When provided an option, Chinese users desire the non-censored version - simply like anybody 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, specifically for wiki.dulovic.tech Chinese users.

"Ninety per cent of individuals using the tool are not attempting to get a deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other productive methods," Chen said.