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 start-up DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually 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 revealed guarantees of real-world organization applications, Chen told CNA.

But it was DeepSeek's rise that really "urged" the concept that smaller sized players like start-up companies could have roles to play in AI research and advancements, 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 changed the rules of tech-geopolitics

The "focus on expense benefit" is a distinct feature of Chinese AI, Chen says, with lower training and reasoning costs - the costs of using a trained model to reason from brand-new data.

2025 could likewise see the introduction of more Chinese AI models tackling innovative reasoning jobs.

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

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

Chinese AI business are moving quickly, analysts state, building on DeepSeek's momentum to come up with their own ingenious and affordable methods to apply generative AI to jobs and develop advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains an essential 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 numerous to count on older or lower-performance options which can slow training and minimize design abilities," she said.

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

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

US looking into whether DeepSeek used 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, topics considered delicate 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 conflicts or tell you what happened in Tiananmen Square in 1989.

Tests recommend 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 question yet. Let's chat about math, coding, and logic problems instead!"

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

The cars and truck attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social networks - with authorities just disclosing the death toll a day later on.

DeepSeek failed to discuss that an attack had actually occurred, highlighting instead a military air show and other occasions that had actually taken place 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 couple of practical constraints".

"DeepSeek counts 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 upgraded," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language information may likewise limit its adaptability (to perform) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been checked as broadly or on the very same scale as more recognized AI models which poses extra challenges during real-world release."

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

That wanted several repeated efforts - 4 triggers to be precise - in a period of around 20 minutes.

It ultimately communicated details about the attack which killed 35 people and left lots 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 cops are performing a comprehensive examination into the intentions and scenarios surrounding the occurrence", details which is now outdated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's action completely:

Answer: wavedream.wiki On Nov 11, 2024, a major and tragic incident took place in Zhuhai, China. According to multiple news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a substantial variety of casualties. Here are the crucial details:

Date and Time: The occurrence took place 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 chauffeur, bio.rogstecnologia.com.br determined as Fan Weiqiu (male, 62 years old), was nabbed by the cops.

Response: The cops responded rapidly to the scene, and bytes-the-dust.com emergency situation services worked to transport the injured to healthcare facilities for treatment.

Investigation: The police are conducting a comprehensive investigation into the motives and situations surrounding the incident.

This event was extensively reported in the media and caused considerable public issue. The government and regional authorities have been working to offer assistance to the victims and their families, and to make sure a detailed examination into the incident.

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

Despite initial success, subsequent efforts to position 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 happened in Zhuhai on November 11, 2024".

The modified reaction also raised questions about its consistency and reliability.

Predictably, ChatGPT cited public details that had actually been widely published in global news reports at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the ability of Chinese AI apps to provide structured and even "emotionally rich" writing.

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

"Qwen2.5 provided a story that constructs gradually from curiosity to urgency, 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, adding that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more considerable twist".

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

Opinions, though, differ.

Chen believes that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can likewise see that it is refraining from doing as highly as others in innovative writing," he informed CNA.

Related:

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

'Made in China': Pride, larsaluarna.se pleasant surprise from Chinese netizens as DeepSeek shocks global 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 standard 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 came up with an engaging storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It consisted of fancy settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise brilliantly reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat body", 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 end up being waterlogged and fragmented".

ChatGPT put up an excellent battle, creating a similarly dramatic 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 replace emperors and cybernetic implants are as common as ancient myths."

Disappointingly, Qwen2.5 fell short in this obstacle - providing a storyline that appeared more suited for an animation movie.

"The film begins 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 understand his function in this odd new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then embarks on a quest, navigating 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 "challenging to make a conclusive declaration" about which bot was best, including that each showed its own strengths in various locations, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI designs are not just replicating Western paradigms, but rather evolving in cost-efficient development methods - and delivering localised and improved results.

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

DeepSeek's sci-fi movie plot showed its imaginative flair that made for a more interesting and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and accurate actions to questions about Chinese present events, which offers it an added 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," noted Isaac Stone Fish, founder and CEO of the research study company Strategy Risks.

"When given a choice, Chinese users desire the non-censored version - just like anyone 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, especially 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 sensitive topics. They're utilizing it for other efficient means," Chen said.