wolvesbaneuo

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: larsaluarna.se Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the country 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 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 investments in Chinese AI accelerated after ChatGPT removed in 2022 and showed promises of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that really "encouraged" the concept that smaller gamers like start-up firms could have roles to play in AI research and developments, he includes.

'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 just altered the guidelines of tech-geopolitics

The "focus on cost benefit" is an unique feature of Chinese AI, Chen states, with lower training and inference costs - the costs of using a trained design to draw conclusions from brand-new data.

2025 might also see the emergence of more Chinese AI designs dealing with sophisticated thinking jobs.

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

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

Chinese AI companies are moving quickly, experts say, constructing on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative AI to tasks and develop more advanced products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains an essential difficulty for Chinese developers, kept in mind Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the ability of Chinese tech business ... requiring numerous to depend on older or lower-performance alternatives which can slow training and minimize design capabilities," she said.

"While some business like DeepSeek, have actually discovered imaginative methods to optimize or utilize more standard hardware effectively, obtaining cutting-edge chips still makes a big difference for training huge AI designs."

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

US looking into whether DeepSeek utilized 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 considered sensitive by the state are censored on the internet so it need 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 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 concern yet. Let's chat about math, coding, and reasoning issues rather!"

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

The cars and truck attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social media - with authorities only divulging the death toll a day later.

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

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

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

"Its strong focus on Chinese-language data may likewise limit its adaptability (to perform) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the very same scale as more established AI models which poses additional obstacles throughout real-world implementation."

When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our concern about the Zhuhai vehicle attack.

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

It ultimately passed on details about the attack which eliminated 35 individuals and left dozens of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the police are performing an extensive examination into the motives and scenarios surrounding the occurrence", details which is now outdated.

The motorist, classificados.diariodovale.com.br Fan, was carried out last month.

This is Qwen2.5's response in full:

Answer: On Nov 11, 2024, a significant and tragic incident occurred in Zhuhai, China. According to multiple news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the crucial details:

Date and Time: The occurrence occurred 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: engel-und-waisen.de The chauffeur, determined as Fan Weiqiu (male, 62 years old), was collared by the police.

Response: The authorities responded quickly to the scene, forum.pinoo.com.tr and emergency situation services worked to transport the injured to health centers for treatment.

Investigation: The police are performing a thorough examination into the motives and scenarios surrounding the occurrence.

This occasion was extensively reported in the media and caused significant public concern. The federal government and local authorities have been working to supply support to the victims and their households, and to guarantee a detailed examination into the occurrence.

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

Despite initial success, subsequent efforts to pose the same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on occasions that occurred in Zhuhai on November 11, 2024".

The altered reaction likewise raised questions about its consistency and dependability.

Predictably, ChatGPT cited public details that had been commonly published in worldwide news reports 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 and even "mentally abundant" writing.

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

"Qwen2.5 delivered a story that constructs gradually from interest to urgency, keeping the reader engaged. It provides 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, mentally abundant story with a more substantial twist".

"DeepSeek wrote a great story however did not have tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, though, vary.

Chen thinks that Qwen2.5 does not perform 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 likewise see that it is refraining from doing as highly as others in innovative writing," he told CNA.

Related:

China's brand-new face of AI: Who is DeepSeek founder Liang Wenfeng?

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts international 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 movie 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 engaging 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 drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise remarkably reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg nightclub owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up a great fight, coming up with an equally significant 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 difficulty - providing a storyline that appeared more fit for an animation film.

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

Realising his brand-new truth and "seeking to comprehend his function in this unusual brand-new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a conclusive declaration" 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 designs are not just replicating Western paradigms, but rather developing in cost-effective innovation approaches - and delivering localised and improved outcomes.

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

DeepSeek's sci-fi movie plot demonstrated its innovative flair that made for a more interesting and creative story as compared to Qwen2.5 and genbecle.com ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual actions to questions about Chinese present occasions, disgaeawiki.info which provides it an added advantage.

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 a choice, Chinese users want the non-censored variation - much like anybody else, so I feel 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 people using the tool are not trying to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other efficient methods," Chen said.