hitbat

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 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 "tactically essential" and its foray 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 investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed pledges of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that really "urged" the concept that smaller sized gamers like start-up firms might have roles to play in AI research study and developments, he adds.

'A lot is up in the air': Is Chinese firm DeepSeek's AI model as impactful as it claims?

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

The "focus on cost benefit" is a distinctive function of Chinese AI, Chen says, with lower training and inference costs - the expenses of utilizing a trained model to reason from brand-new data.

2025 might likewise see the development of more Chinese AI designs tackling advanced thinking jobs.

"We might see some AI companies focusing on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete ways to commercialise their models 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 rapidly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative AI to jobs and establish more advanced items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a crucial hurdle for Chinese developers, noted 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 many to rely on older or lower-performance options which can slow training and lower model abilities," she said.

"While some companies like DeepSeek, have discovered innovative ways to optimize or use more basic hardware efficiently, obtaining cutting-edge chips still makes a huge difference for training huge AI models."

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

US looking into whether DeepSeek used limited AI chips obtained through other countries, 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 considered sensitive by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what happened 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 type of question yet. Let's chat about mathematics, coding, and logic issues rather!"

To further check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact 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 initially greatly censored on Chinese social media - with authorities only divulging the death toll a day later on.

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

Dr Zhang believes that it may be a mix of aspects at play, such as censorship in addition to "a couple of practical constraints".

"DeepSeek relies on a mix of older graphics processing units and has limited access to innovative hardware which can impact 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 information might also limit its flexibility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been checked as broadly or on the same scale as more recognized AI designs which poses additional difficulties throughout real-world implementation."

When it pertained to Qwen2.5, remarkably addressed our concern about the Zhuhai vehicle attack.

That was after multiple repeated attempts - 4 triggers to be exact - in a span of around 20 minutes.

It eventually passed on details about the attack which killed 35 people and left dozens of others hurt, hb9lc.org also going on to note 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 performing an extensive investigation into the motives and scenarios surrounding the occurrence", details which is now dated.

The driver, Fan, was carried out last month.

This is Qwen2.5's reaction in full:

Answer: On Nov 11, 2024, a major and tragic incident took place in Zhuhai, wiki-tb-service.com China. According to numerous news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the crucial details:

Date and Time: The occurrence occurred on November 11, 2024, 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 chauffeur, determined as Fan Weiqiu (male, wavedream.wiki 62 years old), was captured by the cops.

Response: The cops reacted rapidly to the scene, and emergency situation services worked to carry the hurt to medical facilities for treatment.

Investigation: The police are conducting a comprehensive examination into the motives and circumstances surrounding the occurrence.

This event was commonly reported in the media and caused significant public concern. The federal government and regional authorities have actually been working to offer support to the victims and their households, and to ensure a detailed examination into the occurrence.

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

Despite preliminary success, subsequent efforts to position the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".

The transformed reaction also raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had been widely published in global news reports 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 deliver structured and even "mentally abundant" writing.

"DeepSeek-R1 provided a story with a more reflective tone and smoother psychological shifts for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds slowly from interest to seriousness, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery 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 apparent option."

Opinions, though, vary.

Chen thinks that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to innovative 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 new face of AI: Who is DeepSeek creator Liang Wenfeng?

'Made in China': Pride, yewiki.org enjoyable surprise from Chinese netizens as DeepSeek shocks international AI scene

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

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

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

It also remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg club owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed an excellent battle, developing a similarly remarkable cyberpunk storyline which likewise 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 challenge - providing a storyline that seemed more fit for an animation movie.

"The film starts with the awakening of Sun Wukong within a modern research study facility situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "looking for to comprehend his function in this weird new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not just reproducing Western paradigms, however rather developing in economical development techniques - and providing localised and improved results.

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

DeepSeek's sci-fi movie plot demonstrated its imaginative flair that produced a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual responses to concerns about Chinese present events, it-viking.ch which gives 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 company Strategy Risks.

"When given an option, 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, particularly for Chinese users.

"Ninety percent of individuals using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other efficient means," Chen said.