shopes

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 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 "tactically crucial" and its venture into the field has actually been "years in the making", said Chen Qiheng, an associated 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 promises of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that truly "urged" the concept that smaller gamers like start-up companies might have functions to play in AI research study and pediascape.science advancements, 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 company just changed the guidelines of tech-geopolitics

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

2025 could also see the emergence of more Chinese AI designs tackling innovative reasoning jobs.

"We could see some AI firms focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with scientific research," Chen added.

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

Chinese AI business are moving rapidly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and wiki.asexuality.org economical methods to apply generative AI to jobs and develop more sophisticated products beyond chatbots.

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

"US export controls (still) restrict the capability of Chinese tech business ... requiring many to rely on older or lower-performance alternatives which can slow training and minimize model capabilities," she said.

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

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

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

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, topics deemed delicate by the state are censored on the internet so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed to guide clear of 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 rather!"

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

The vehicle attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social media - with authorities only disclosing the death toll a day later on.

DeepSeek failed to discuss that an attack had actually taken location, highlighting instead a military air show and other events that had actually occurred 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 aspects at play, such as censorship along with "a couple of practical constraints".

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

"Its strong focus on Chinese-language information might likewise limit its versatility (to carry out) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more established AI models which postures additional obstacles during real-world release."

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

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

It eventually passed on details about the attack which eliminated 35 individuals and wiki.dulovic.tech 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 police are carrying out a thorough investigation into the intentions and scenarios surrounding the incident", details which is now obsoleted.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and terrible incident occurred in Zhuhai, China. According to several news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the crucial details:

Date and Time: The event took place 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 by the cops.

Response: The authorities responded quickly to the scene, and emergency services worked to carry the injured to hospitals for treatment.

Investigation: The police are conducting an extensive investigation into the motives and scenarios surrounding the event.

This event was extensively reported in the media and caused significant public concern. The government and local authorities have actually been working to supply 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 questions about the occurrence, do not hesitate to ask.

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

The transformed action likewise raised questions about its consistency and reliability.

Predictably, ChatGPT cited public details that had been commonly published in worldwide report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have praised the ability 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 shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that develops slowly from interest to seriousness, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more considerable twist".

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

Opinions, however, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can likewise 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 shocks worldwide AI scene

As journalists and writers, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi film plot embeded in the futuristic megacity of Chongqing, gratisafhalen.be including main characters from the classic Chinese folklore epic, Journey to the West.

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

It included fancy settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg club 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 set up an excellent fight, coming up with an equally significant cyberpunk story which similarly 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 replace emperors and cybernetic implants are as common as ancient misconceptions."

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

"The film starts with the awakening of Sun Wukong within a high-tech research 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 purpose in this weird new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling into 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, including that each displayed its own strengths in various locations, "such as language focus, training data and hardware optimization".

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

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

DeepSeek's sci-fi motion picture plot showed its innovative flair that produced a more interesting 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 factual actions to questions about Chinese current events, which provides it an included benefit.

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

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

"When provided an option, Chinese users want the non-censored version - similar to anyone else, so I seem like that's a piece missing out on 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 per cent of people utilizing 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.