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 produced 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 objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "strategically essential" and it-viking.ch its venture into the field has 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 financial investments in Chinese AI sped up after ChatGPT took off in 2022 and showed promises of real-world organization applications, Chen told CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized gamers like start-up companies might have roles to play in AI research and archmageriseswiki.com advancements, he includes.

'A lot is up in the air': forum.pinoo.com.tr Is Chinese company DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI company simply changed the guidelines of tech-geopolitics

The "emphasis on expense benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning costs - the costs of utilizing a trained design to draw conclusions from brand-new data.

2025 might likewise see the introduction of more Chinese AI designs taking on advanced thinking jobs.

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

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

Chinese AI business are moving quickly, analysts say, constructing on DeepSeek's momentum to come up with their own ingenious and cost-efficient methods to apply generative AI to jobs and develop more sophisticated products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial hurdle 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 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 found imaginative methods to optimize or utilize more fundamental hardware effectively, obtaining cutting-edge chips still makes a huge difference for training really large AI models."

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

US checking out whether DeepSeek utilized 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, subjects considered delicate by the state are censored on the internet so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to avoid domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this type of concern yet. Let's chat about mathematics, coding, and logic issues rather!"

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

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

DeepSeek failed to point out that an attack had actually taken place, highlighting instead a military air show and other events that had actually occurred in the city like singles' day shopping sales as well as sports and cultural activities.

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

"DeepSeek counts on a mix of older graphics processing systems and has actually limited access to innovative 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 focus on Chinese-language data may likewise limit its versatility (to bring out) multilingual tasks ... As a fairly brand-new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the very same scale as more recognized AI models which presents additional difficulties throughout real-world release."

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

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

It eventually communicated details about the attack which killed 35 people and 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, along with casualties.

However, it wrote that "the police are performing a thorough examination into the motives and circumstances surrounding the occurrence", details which is now dated.

The motorist, Fan, was executed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and tragic event took place in Zhuhai, China. According to several news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a considerable number of casualties. Here are the key details:

Date and Time: The occurrence happened on November 11, 2024, wiki.asexuality.org at around 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 apprehended by the police.

Response: The police responded quickly to the scene, and emergency situation services worked to transfer the hurt to hospitals for treatment.

Investigation: The cops are conducting an extensive examination into the motives and scenarios surrounding the event.

This occasion was commonly reported in the media and triggered considerable public concern. The government and regional authorities have actually been working to supply assistance to the victims and their families, and to ensure a detailed investigation into the event.

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

Despite initial success, trademarketclassifieds.com subsequent attempts to posture the exact same to Qwen2.5 led to the censors back at work with the reply "I don't have particular details on occasions that took place in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had been widely released in international 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 provide structured and even "mentally abundant" writing.

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

"Qwen2.5 delivered a story that builds gradually from curiosity to urgency, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek composed a great story however lacked tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, however, differ.

Chen believes 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 also see that it is refraining from doing as strongly as others in innovative writing," he informed CNA.

Related:

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

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts global AI scene

As journalists and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot set in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek developed 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 intricate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It also brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg bar 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 installed a good fight, coming up with a similarly dramatic cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

"This is a world where AI deities rule, corporations replace emperors and cybernetic implants are as typical as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this difficulty - providing a story that appeared more matched for an animation movie.

"The motion picture begins with the awakening of Sun Wukong within a high-tech research study center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new truth and "seeking to understand his function in this weird new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then starts 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 "difficult 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 information and hardware optimization".

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

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

DeepSeek's sci-fi motion picture plot showed its creative flair that made for a more appealing and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual reactions to questions 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 downside when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research study firm Strategy Risks.

"When given a choice, Chinese users desire the non-censored variation - just 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, yewiki.org specifically for Chinese users.

"Ninety percent of people using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient ways," Chen said.