elaad

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 becoming the world leader in AI by 2030.

China views AI as being "strategically crucial" and its venture into the field has actually 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 showed pledges of real-world organization applications, Chen told CNA.

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

The "focus on expense benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference costs - the expenses of using a trained design to draw conclusions from new data.

2025 could likewise see the development of more Chinese AI designs tackling advanced reasoning jobs.

"We might see some AI firms focusing on getting closer to artificial general intelligence (AGI) while others concentrate on concrete methods to commercialise their models and integrate them with scientific research," Chen included.

AGI refers to a system with intelligence on par with human capabilities.

Chinese AI business are moving rapidly, analysts state, constructing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative AI to jobs and develop more advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential obstacle for Chinese designers, 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 capability of Chinese tech business ... forcing lots of to count on older or lower-performance options which can slow training and lower model abilities," she said.

"While some companies like DeepSeek, have discovered imaginative methods to enhance or utilize more standard hardware efficiently, obtaining advanced chips still makes a huge difference for training extremely large AI designs."

DeepSeek-Nvidia chips: Singapore states it expects companies to abide by its laws

US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, 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, subjects deemed sensitive by the state are censored on the web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed 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 math, coding, and logic problems rather!"

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

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

DeepSeek failed to mention that an attack had taken place, highlighting rather a military air program and other occasions that had taken place in the city like singles' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it might be a mix of elements at play, bytes-the-dust.com such as censorship in addition to "a couple of useful constraints".

"DeepSeek depends on a mix of older graphics processing systems and has restricted access to cutting-edge hardware which can impact how quickly and extensively the design can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data might also limit its flexibility (to perform) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been evaluated as broadly or on the same scale as more established AI models which positions additional difficulties during real-world deployment."

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

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

It eventually relayed details about the attack which killed 35 people and left dozens of others injured, likewise going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it composed that "the cops are performing a comprehensive examination into the motives and scenarios surrounding the event", details which is now outdated.

The driver, Fan, was carried out last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and awful event took place in Zhuhai, China. According to several news sources, a guy 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 substantial number of casualties. Here are the essential details:

Date and Time: The event happened on November 11, 2024, at around 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, determined as Fan Weiqiu (male, 62 years of ages), was apprehended by the authorities.

Response: The cops reacted rapidly to the scene, and emergency services worked to transfer the injured to health centers for treatment.

Investigation: The authorities are carrying out an extensive examination into the intentions and situations surrounding the incident.

This event was commonly reported in the media and triggered significant public issue. The government and local authorities have been working to supply support 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, surgiteams.com subsequent efforts to pose the exact 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 transformed response also raised questions about its consistency and reliability.

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

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 used a story with a more introspective tone and smoother psychological transitions 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 offers an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more significant twist".

"DeepSeek composed an excellent story however did not have tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, however, differ.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however 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, pleasant surprise from Chinese netizens as DeepSeek jolts 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 fundamental sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, 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 consisted of intricate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg bar owner "drowning in debt 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 a good battle, creating a similarly dramatic cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".

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

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a storyline that seemed more fit for an animation film.

"The motion picture starts 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 brand-new reality and "looking for to understand his purpose in this weird new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a definitive statement" about which bot was best, adding that each displayed its own strengths in various locations, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI models are not just duplicating Western paradigms, however rather progressing in cost-efficient innovation approaches - and delivering localised and improved results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and accurate actions to questions about Chinese current events, which provides it an added benefit.

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

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

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

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

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