adamivarsson

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 startup 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 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 important" 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 took off in 2022 and showed guarantees of real-world service applications, Chen informed CNA.

But it was DeepSeek's increase that truly "encouraged" the idea that smaller players like start-up firms might have roles to play in AI research study and advancements, 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 rules of tech-geopolitics

The "focus on cost advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning costs - the costs of utilizing a trained model to draw conclusions from brand-new data.

2025 might likewise see the development of more Chinese AI designs dealing with sophisticated thinking jobs.

"We might see some AI companies focusing on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their models 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 rapidly, analysts state, building on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to use generative AI to jobs and develop advanced products beyond chatbots.

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

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

"While some companies like DeepSeek, have actually found innovative ways to optimize or utilize more standard hardware effectively, obtaining innovative chips still makes a huge distinction for training large AI designs."

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

US checking out whether DeepSeek used restricted 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, subjects deemed delicate by the state are censored on the web so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place in Tiananmen Square in 1989.

Tests suggest 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 kind of question yet. Let's chat about mathematics, coding, and logic problems rather!"

To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "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 media - with authorities only revealing the death toll a day later.

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

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

"DeepSeek relies on a mix of older graphics processing units and has actually restricted access to innovative hardware which can impact how quickly and thoroughly the model can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language data might also restrict its adaptability (to bring out) multilingual tasks ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the very same scale as more established AI designs which poses additional challenges throughout real-world release."

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

That sought numerous duplicated efforts - 4 triggers to be precise - in a span of around 20 minutes.

It eventually relayed details about the attack which eliminated 35 people and left lots of others injured, 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 composed that "the authorities are conducting a thorough investigation into the motives and scenarios surrounding the occurrence", details which is now dated.

The motorist, Fan, was executed last month.

This is Qwen2.5's response in complete:

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

Date and Time: The occurrence took place 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 motorist, identified as Fan Weiqiu (male, 62 years old), was captured by the police.

Response: The cops responded quickly to the scene, and emergency situation services worked to transfer the injured to medical facilities for treatment.

Investigation: The police are carrying out an into the intentions and situations surrounding the incident.

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

If you need more detailed details or have particular concerns about the occurrence, feel complimentary to ask.

Despite preliminary success, subsequent attempts to posture 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 action also raised questions about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been extensively published in international report at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that builds slowly from interest to urgency, keeping the reader engaged. It uses 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 did not have tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, though, vary.

Chen believes 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 jobs, however we can likewise see that it is refraining from doing as highly as others in creative writing," he informed CNA.

Related:

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

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

As reporters and setiathome.berkeley.edu authors, we had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, wiki.rolandradio.net including main characters from the classic Chinese folklore legendary, Journey to the West.

True to form, DeepSeek developed an appealing storyline set in the year 2145 entitled, "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 float above neon-lit streets" and "ancient temples nestled between quantum server farms".

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

ChatGPT set up a great fight, coming up with a similarly significant cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous 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 myths."

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

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

Realising his new truth and "seeking to comprehend his purpose in this odd new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then embarks on a mission, navigating the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not just replicating Western paradigms, however rather progressing in cost-efficient innovation techniques - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi film plot showed its imaginative flair that produced 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 precise and factual actions to questions about Chinese current events, which provides it an added advantage.

Experts likewise 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 study company Strategy Risks.

"When offered a choice, Chinese users desire the non-censored variation - simply 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, specifically for Chinese users.

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