How do Chinese aI Bots Stack up Against ChatGPT?

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 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 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 ending up being 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 researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed promises of real-world company applications, Chen told CNA.

But it was DeepSeek's increase that actually "encouraged" the concept that smaller players 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 company DeepSeek's AI design as impactful as it claims?

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

The "emphasis on expense benefit" is a distinct function of Chinese AI, Chen states, with lower training and inference costs - the costs of utilizing a trained design to reason from new data.

2025 could likewise see the development of more Chinese AI designs taking on innovative thinking tasks.

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

AGI describes 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 use generative AI to jobs and establish more advanced items beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a key hurdle for Chinese developers, noted 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 business ... forcing lots of to depend on older or lower-performance options which can slow training and lower model abilities," she said.

"While some business like DeepSeek, have found innovative methods to optimize or utilize more basic hardware effectively, obtaining innovative chips still makes a big difference for training extremely large AI models."

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

US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, 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 deemed sensitive by the state are censored on the internet so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are set to avoid domestic politics.

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

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

The automobile attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities just revealing the death toll a day later.

DeepSeek failed to mention that an attack had happened, highlighting rather a military air show and other events that had taken place in the city like singles' day shopping sales as well as sports and cultural activities.

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

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

"Its strong focus on Chinese-language data might likewise limit its flexibility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more established AI designs which postures additional challenges throughout real-world deployment."

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

That sought numerous repeated attempts - four triggers to be precise - in a period of around 20 minutes.

It ultimately relayed details about the attack which killed 35 individuals and left dozens of others injured, also going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that "the authorities are conducting a thorough investigation into the motives and circumstances surrounding the event", details which is now outdated.

The motorist, Fan, was carried out last month.

This is Qwen2.5's action in complete:

Answer: On Nov 11, 2024, a significant and terrible event occurred in Zhuhai, China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the essential 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 resulted in 35 deaths and 43 injuries.

Perpetrator: The driver, recognized as Fan Weiqiu (male, 62 years old), was apprehended by the cops.

Response: The authorities reacted rapidly to the scene, and emergency situation services worked to transfer the injured to health centers for treatment.

Investigation: The police are carrying out a thorough examination into the motives and scenarios surrounding the incident.

This occasion was commonly reported in the media and triggered considerable public issue. The federal government and local authorities have actually been working to supply support to the victims and their households, and to guarantee a detailed examination into the occurrence.

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

Despite initial success, subsequent attempts to present the exact same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that took place in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT cited public details that had actually been extensively published in global news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

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

"DeepSeek composed a great story however lacked stress and an impactful climax, making Qwen2.5 the apparent option."

Opinions, though, vary.

Chen thinks that Qwen2.5 does not carry out as strongly 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 creative writing," he told CNA.

Related:

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

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

As reporters and writers, we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi film plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore impressive, Journey to the West.

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

It consisted of elaborate 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 standard heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight 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 end up being waterlogged and fragmented".

ChatGPT installed an excellent battle, developing an equally remarkable cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary 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 challenge - providing a storyline that appeared more suited for an animation movie.

"The motion picture starts with the awakening of Sun Wukong within a modern research study center located 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 function in this odd brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, navigating the streets of Chongqing to protect the sacred "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not simply duplicating Western paradigms, but rather developing in cost-effective innovation methods - and delivering localised and improved results.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers precise and factual responses to questions about Chinese current occasions, which gives it an included benefit.

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

"DeepSeek is at a disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When offered an option, Chinese users want the non-censored variation - simply like anybody else, so I feel like that's a piece missing out on 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 per cent of individuals utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other efficient methods," Chen said.

返回列表

How do Chinese aI Bots Stack up Against ChatGPT?

[收藏此主题] [关注此主题的新回复]

[通过 QQ、MSN 分享给朋友]