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 start-up DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, surgiteams.com 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 "strategically essential" and forum.batman.gainedge.org its foray into the field has been "years in the making", said Chen Qiheng, an affiliated scientist at the Asia Society Policy Institute's Center for higgledy-piggledy.xyz China Analysis.

Private and public financial investments in Chinese AI accelerated after ChatGPT removed in 2022 and revealed guarantees of real-world service applications, Chen told CNA.

But it was DeepSeek's increase that really "urged" the idea that smaller sized gamers like start-up companies could 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 simply altered the guidelines of tech-geopolitics

The "emphasis on expense advantage" is an unique feature of Chinese AI, Chen says, with lower training and reasoning costs - the costs of utilizing a trained design to reason from new information.

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

"We might see some AI companies 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 study," Chen included.

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

Chinese AI companies are moving quickly, wiki.dulovic.tech analysts state, constructing on DeepSeek's momentum to come up with their own ingenious and economical ways to apply generative AI to tasks and develop advanced items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a key obstacle 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 numerous to count on older or lower-performance options which can slow training and reduce model abilities," she said.

"While some business like DeepSeek, have actually discovered innovative ways to enhance or use more basic hardware efficiently, obtaining advanced chips still makes a big distinction for training huge AI models."

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

US looking into whether DeepSeek used restricted AI chips obtained through other nations, 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, topics deemed sensitive by the state are censored on the internet so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set 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 math, coding, and logic issues rather!"

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

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

DeepSeek failed to point out that an attack had taken location, highlighting instead a military air program and other events that had actually happened in the city like singles' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it might be a mix of elements at play, such as censorship along with "a few practical constraints".

"DeepSeek relies on a mix of older graphics processing systems and has actually restricted access to innovative 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 focus on Chinese-language data might likewise limit its versatility (to carry out) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more established AI models which poses additional challenges throughout real-world implementation."

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

That sought numerous repeated attempts - 4 prompts to be precise - in a period of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 people and left dozens of others hurt, 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 cops are carrying out a thorough examination into the motives and circumstances surrounding the incident", details which is now dated.

The driver, Fan, was executed last month.

This is Qwen2.5's response in complete:

Answer: On Nov 11, 2024, a significant and happened in Zhuhai, China. According to several news sources, a man called Fan Weiqiu (樊某, yewiki.org 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 crucial details:

Date and Time: The occurrence happened on November 11, 2024, at approximately 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, identified as Fan Weiqiu (male, 62 years old), was nabbed by the police.

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

Investigation: forum.batman.gainedge.org The police are conducting a thorough examination into the motives and situations surrounding the occurrence.

This occasion was extensively reported in the media and triggered considerable public concern. The government and local authorities have been working to offer assistance to the victims and their households, and to ensure a detailed investigation into the event.

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

Despite initial success, subsequent attempts to posture the very same concern to Qwen2.5 led to 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 modified response likewise raised concerns about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had been commonly released in international report 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 offered a story with a more introspective tone and smoother emotional transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that develops gradually from interest to seriousness, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more substantial twist".

"DeepSeek wrote a good story but lacked tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, though, differ.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to imaginative 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 innovative writing," he told CNA.

Related:

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

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

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

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

It consisted of 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 traditional 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 "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up an excellent fight, developing a similarly remarkable cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities rule, corporations replace emperors and cybernetic implants are as common as ancient misconceptions."

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

"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 "looking for to comprehend his function in this strange new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a conclusive 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 highlights how Chinese AI models are not simply reproducing Western paradigms, but rather evolving in affordable innovation techniques - and delivering localised and enhanced results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate reactions to questions about Chinese current occasions, which provides it an added advantage.

Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.

"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When given a choice, Chinese users want the non-censored variation - just like anybody else, so I seem like that's a piece missing from it."

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

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