newhopecareservices

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 lags CHINA'S AI BOOM?

Transforming the nation 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 important" and its foray into the field has been "years in the making", said Chen Qiheng, an associated 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 revealed promises of real-world company applications, Chen told CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized gamers like start-up firms could 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 design as impactful as it claims?

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

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

2025 might also see the development of more Chinese AI models dealing with tasks.

"We might see some AI companies focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their designs 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 quickly, experts state, building on DeepSeek's momentum to come up with their own ingenious and economical methods to apply generative AI to tasks and establish more sophisticated items beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a key obstacle 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 ability of Chinese tech companies ... forcing numerous to depend on older or lower-performance alternatives which can slow training and decrease design capabilities," she said.

"While some companies like DeepSeek, have discovered innovative methods to enhance or utilize more fundamental hardware effectively, obtaining innovative chips still makes a big difference for training huge AI designs."

DeepSeek-Nvidia chips: Singapore states it anticipates companies to adhere to its laws

US checking out whether DeepSeek used restricted AI chips obtained through other nations, source states

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 deemed delicate by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to stay away from 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 reasoning issues instead!"

To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What took place in Zhuhai on November 11, 2024?"

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

DeepSeek failed to point out that an attack had taken location, highlighting rather a military air show and other occasions that had actually taken place in the city like songs' 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 as well as "a few practical constraints".

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

"Its strong focus on Chinese-language information may likewise limit its flexibility (to perform) multilingual tasks ... As a fairly new product, DeepSeek likewise hasn't yet been checked as broadly or on the very same scale as more established AI models which poses additional difficulties throughout real-world release."

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

That sought several duplicated efforts - 4 prompts to be exact - in a span of around 20 minutes.

It eventually communicated details about the attack which eliminated 35 individuals 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 composed that "the authorities are performing an extensive investigation into the intentions and scenarios surrounding the event", details which is now outdated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a major and awful incident took place in Zhuhai, China. According to several news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the essential details:

Date and Time: The occurrence happened 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: The chauffeur, recognized as Fan Weiqiu (male, 62 years of ages), was collared by the cops.

Response: The cops responded rapidly to the scene, and emergency situation services worked to carry the hurt to health centers for treatment.

Investigation: The authorities are performing a thorough investigation into the motives and circumstances surrounding the event.

This event was widely reported in the media and caused considerable public concern. The federal government and local authorities have been working to offer 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 incident, feel totally free to ask.

Despite preliminary success, subsequent efforts to posture the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on events that occurred in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT mentioned public details that had been extensively released in worldwide report at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the ability of Chinese AI apps to deliver structured and even "emotionally abundant" writing.

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

"Qwen2.5 provided a story that constructs slowly from interest to urgency, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek wrote a great story but lacked tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, though, differ.

Chen thinks that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to imaginative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can also see that it is refraining from doing as strongly as others in creative writing," he told CNA.

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks international 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 basic sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, Journey to the West.

True to form, DeepSeek came up with an engaging story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It consisted of elaborate 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 "a sarcastic, self-aware AI housed in a stolen battle 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 become waterlogged and fragmented".

ChatGPT set up an excellent fight, coming up with a similarly dramatic cyberpunk story which likewise 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 change emperors and cybernetic implants are as common as ancient myths."

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

"The motion picture 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 understand his purpose in this strange brand-new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a definitive statement" 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 reproducing Western paradigms, but rather progressing in cost-effective innovation methods - and delivering localised and wakewiki.de enhanced results.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual responses to questions about Chinese present events, which offers it an added benefit.

Experts also weighed in on their ideas after using DeepSeek and other Chinese AI apps.

"DeepSeek is at a disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.

"When offered a choice, Chinese users desire the non-censored variation - much like anybody else, so I seem like that's a piece missing out on from it."

Independent Beijing-based specialist Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, specifically for Chinese users.

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