marcosurrey

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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

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

China views AI as being "tactically essential" and its venture into the field has 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 accelerated after ChatGPT removed in 2022 and showed pledges of real-world organization applications, Chen informed CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller players like start-up firms could have roles to play in AI research and advancements, 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 company simply changed the rules of tech-geopolitics

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

2025 could likewise see the emergence of more Chinese AI models dealing with advanced reasoning tasks.

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

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

Chinese AI companies are moving quickly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and cost-effective methods to use generative AI to jobs and establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a key difficulty 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 capability of Chinese tech companies ... requiring lots of to depend on older or lower-performance options which can slow training and reduce design capabilities," she said.

"While some business like DeepSeek, have found creative ways to optimize or utilize more standard hardware effectively, obtaining advanced chips still makes a huge distinction for training extremely big AI designs."

DeepSeek-Nvidia chips: Singapore says it anticipates business to comply with its laws

US looking into whether DeepSeek used limited AI chips obtained through other nations, 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 web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what happened 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 math, coding, and logic problems rather!"

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

The car attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social media - with authorities only disclosing the death toll a day later on.

DeepSeek failed to mention that an attack had taken place, highlighting instead a military air program and other occasions that had actually occurred in the city like singles' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it might be a mix of elements at play, such as censorship along with "a few practical constraints".

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

"Its strong concentrate on Chinese-language data may likewise restrict its versatility (to bring out) multilingual tasks ... 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 designs which positions extra challenges during real-world implementation."

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

That wanted multiple repeated efforts - 4 prompts to be accurate - in a period of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 individuals and left dozens of others injured, 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 wrote that "the police are conducting an extensive investigation into the intentions and scenarios surrounding the occurrence", details which is now outdated.

The driver, Fan, was executed last month.

This is Qwen2.5's reaction in complete:

Answer: On Nov 11, 2024, a major and tragic occurrence happened in Zhuhai, China. According to multiple news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, pipewiki.org resulting in a considerable number of casualties. Here are the essential details:

Date and Time: The event occurred on November 11, bytes-the-dust.com 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 authorities.

Response: The police reacted rapidly to the scene, and emergency services worked to transport the hurt to health centers for treatment.

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

This event was extensively reported in the media and triggered significant public issue. The federal government and regional authorities have actually been working to supply assistance to the victims and their households, and to ensure a detailed investigation into the event.

If you require more detailed details or have specific questions about the occurrence, do not hesitate to ask.

Despite preliminary success, subsequent efforts to pose the same question to Qwen2.5 led to the censors back at work with the reply "I do not have specific details on events that took place in Zhuhai on November 11, 2024".

The altered action also raised questions about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been widely published in worldwide report at the time of the mishap - so not a 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 offered a story with a more reflective tone and smoother emotional transitions for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

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

"DeepSeek composed a great story but lacked tension and an impactful climax, making Qwen2.5 the apparent 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 founder Liang Wenfeng?

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

As reporters and authors, 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 set in the futuristic megacity of Chongqing, classificados.diariodovale.com.br including main characters from the classic Chinese folklore legendary, Journey to the West.

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

It included intricate 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 likewise brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg bar owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed a good battle, creating an equally remarkable cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities guideline, corporations change emperors and cybernetic implants are as common as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a storyline that appeared more suited for an animation film.

"The film starts with the awakening of Sun Wukong within a high-tech research center situated 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 unusual new world", he then leaves and photorum.eclat-mauve.fr meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not simply duplicating Western paradigms, but rather progressing in cost-effective development techniques - and delivering localised and enhanced results.

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

DeepSeek's sci-fi film plot showed its creative flair that produced a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, pipewiki.org offers accurate and accurate reactions to concerns about Chinese existing occasions, which provides it an included .

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

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

"When offered an option, Chinese users desire the non-censored version - similar to anyone else, so I seem like that's a piece missing out on from it."

Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly for Chinese users.

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