vidconnect

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'S BEHIND CHINA'S AI BOOM?

Transforming the country 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 "strategically important" 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 sped up after ChatGPT took off in 2022 and revealed promises of real-world organization applications, Chen informed CNA.

But it was DeepSeek's increase that actually "urged" the concept that smaller gamers like start-up companies could have roles 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 just changed the guidelines of tech-geopolitics

The "emphasis on cost benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference expenses - the expenses of utilizing a trained design to draw conclusions from brand-new data.

2025 might also see the emergence of more Chinese AI models tackling advanced thinking jobs.

"We could see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others focus on concrete methods to commercialise their designs and incorporate them with clinical research," Chen included.

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

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

But on the other hand, access to high-end hardware, especially Nvidia's innovative 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) limit the capability of Chinese tech companies ... requiring numerous to count on older or lower-performance alternatives which can slow training and minimize model capabilities," she said.

"While some business like DeepSeek, have actually discovered imaginative ways to optimize or use more basic hardware effectively, obtaining advanced chips still makes a big difference for training large AI models."

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

US checking out whether DeepSeek used limited 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 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 disputes or tell you what took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured 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 math, coding, and reasoning problems 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 automobile attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social media - with authorities just disclosing the death toll a day later on.

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

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

"DeepSeek counts on a mix of older graphics processing systems and has limited access to innovative hardware which can affect how quickly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may also restrict its versatility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the same scale as more recognized AI designs which positions extra obstacles throughout real-world implementation."

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

That was after numerous duplicated efforts - four prompts to be exact - in a period of around 20 minutes.

It eventually passed on details about the attack which eliminated 35 individuals and left lots of others hurt, likewise 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 police are conducting a comprehensive examination into the motives and situations surrounding the event", details which is now dated.

The motorist, Fan, was performed last month.

This is Qwen2.5's action in full:

Answer: On Nov 11, 2024, a major and terrible occurrence occurred in Zhuhai, China. According to multiple news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, higgledy-piggledy.xyz resulting in a significant number of casualties. Here are the essential details:

Date and Time: The incident happened 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, identified as Fan Weiqiu (male, 62 years old), was nabbed by the police.

Response: The authorities reacted rapidly to the scene, and emergency services worked to transfer the hurt to medical facilities for treatment.

Investigation: The cops are performing a thorough examination into the intentions and scenarios surrounding the occurrence.

This event was widely reported in the media and caused substantial public issue. The government and regional authorities have been working to provide support to the victims and their families, and to guarantee a detailed investigation into the occurrence.

If you require more detailed details or have particular concerns about the event, do not hesitate to ask.

Despite preliminary success, subsequent attempts to position the very same question 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 altered response likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had been extensively released in international report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 used a story with a more reflective tone and smoother psychological transitions for a well-paced story," composed 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 provides an unforeseen 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, emotionally abundant story with a more significant twist".

"DeepSeek composed an excellent story however lacked tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, however, vary.

Chen believes 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, however we can likewise see that it is refraining from doing as highly as others in innovative writing," he informed CNA.

Related:

China's new face of AI: Who is DeepSeek creator systemcheck-wiki.de Liang Wenfeng?

'Made in China': bio.rogstecnologia.com.br Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts worldwide 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 basic sci-fi film plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore legendary, 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 merges with quantum computing".

It consisted of elaborate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, surgiteams.com whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed a great battle, creating an equally remarkable 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 rule, corporations change emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this challenge - providing a story that appeared more fit for an animation film.

"The film starts with the awakening of Sun Wukong within a state-of-the-art 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 understand his function in this weird new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then starts a mission, yewiki.org browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into 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 various areas, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not simply replicating Western paradigms, however 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 movie plot showed its imaginative flair that produced a more interesting and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers precise and accurate responses to concerns about Chinese present occasions, 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 and CEO of the research firm Strategy Risks.

"When given a choice, Chinese users desire the non-censored version - much 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, specifically for users.

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