mypocket

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 nation into a tech superpower has 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 "tactically important" and its venture into the field has been "years in the making", said Chen Qiheng, an affiliated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed guarantees of real-world service applications, Chen informed CNA.

But it was DeepSeek's rise that truly "urged" the idea that smaller gamers like start-up firms might have functions to play in AI research and advancements, he includes.

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

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

The "emphasis on expense advantage" is a distinct feature of Chinese AI, Chen states, with lower training and reasoning expenses - the costs of using a trained design to draw conclusions from new data.

2025 could likewise see the emergence of more Chinese AI designs taking on sophisticated reasoning jobs.

"We could see some AI firms concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with scientific research," Chen added.

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

Chinese AI business are moving rapidly, experts say, developing on DeepSeek's momentum to come up with their own ingenious and affordable ways to apply generative AI to jobs and develop more innovative items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a key obstacle for Chinese developers, 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 business ... forcing numerous to depend on older or lower-performance options which can slow training and decrease design abilities," she said.

"While some companies like DeepSeek, have actually discovered creative ways to enhance or utilize more standard hardware efficiently, obtaining advanced chips still makes a big distinction for training huge AI designs."

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

US checking out whether DeepSeek used limited AI chips obtained through other countries, source states

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 must come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform 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 question yet. Let's chat about math, coding, and logic issues rather!"

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

The automobile attack outside a sports stadium in the southern Chinese city was at first heavily 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 occurred, highlighting instead a military air show and other occasions that had occurred 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 factors at play, such as censorship in addition to "a couple of practical constraints".

"DeepSeek depends on a mix of older graphics processing units and has actually restricted access to advanced hardware which can affect how rapidly and thoroughly the design can be trained or upgraded," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language information might likewise restrict its flexibility (to perform) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been evaluated as broadly or on the same scale as more established AI designs which postures extra difficulties throughout real-world release."

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

That wanted several duplicated efforts - four prompts to be accurate - in a period of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 people and left dozens of others injured, also going on to note details like the date and time, details about the assailant including his name and systemcheck-wiki.de age, in addition to casualties.

However, it wrote that "the cops are carrying out a comprehensive examination into the motives and circumstances surrounding the event", details which is now outdated.

The driver, Fan, was carried out last month.

This is Qwen2.5's action in complete:

Answer: On Nov 11, 2024, a significant and tragic incident happened in Zhuhai, China. According to several news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the essential details:

Date and Time: it-viking.ch The event took place on November 11, 2024, at roughly 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 motorist, identified as Fan Weiqiu (male, 62 years of ages), was apprehended by the authorities.

Response: The cops responded rapidly to the scene, and engel-und-waisen.de emergency situation services worked to transfer the hurt to health centers for treatment.

Investigation: The authorities are carrying out a comprehensive investigation into the motives and situations surrounding the incident.

This event was extensively reported in the media and triggered considerable public concern. The government and regional authorities have been working to supply support to the victims and their households, and to guarantee a detailed examination into the event.

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

Despite preliminary success, subsequent attempts to posture the exact same concern to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on events that took place in Zhuhai on November 11, 2024".

The modified action also raised concerns about its consistency and reliability.

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

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 offered 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 provided a story that constructs gradually from interest to seriousness, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek wrote an excellent story however did not have stress and an impactful climax, making Qwen2.5 the evident choice."

Opinions, however, vary.

Chen thinks 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, but we can also see that it is refraining from doing as highly as others in imaginative 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 jolts worldwide 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 motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore epic, Journey to the West.

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

It included sophisticated settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also 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 installed a good fight, creating an equally remarkable 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 misconceptions."

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

"The motion picture begins 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 function in this strange new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then embarks on a quest, navigating the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "tough 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 data and hardware optimization".

Her insight underscores how Chinese AI designs are not just replicating Western paradigms, however rather evolving in affordable innovation approaches - and providing localised and enhanced results.

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

DeepSeek's sci-fi film plot demonstrated its creative flair that made for wiki.vst.hs-furtwangen.de a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate actions to concerns about Chinese present occasions, which gives it an added advantage.

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," noted Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.

"When given an option, Chinese users want the non-censored version - much like anyone else, so I feel 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 per cent of individuals using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other productive methods," Chen said.