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, AFP/Sebastien Bozon)

This audio is generated 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 "tactically important" and its foray 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 financial investments in Chinese AI sped up after ChatGPT removed in 2022 and showed guarantees of real-world service applications, Chen told CNA.

But it was DeepSeek's increase that actually "urged" the concept that smaller sized gamers like start-up companies could have roles to play in AI research and advancements, he includes.

'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 company just changed the guidelines of tech-geopolitics

The "focus on cost advantage" is a distinct feature of Chinese AI, Chen says, with lower training and inference expenses - the costs of utilizing a trained model to reason from brand-new data.

2025 could likewise see the introduction of more Chinese AI models tackling advanced reasoning jobs.

"We might see some AI firms focusing on getting closer to artificial general intelligence (AGI) while others focus on concrete ways to commercialise their models and incorporate them with clinical research," Chen added.

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

Chinese AI companies are moving rapidly, analysts say, constructing on DeepSeek's momentum to come up with their own ingenious and economical ways to apply generative AI to tasks and establish advanced items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a key difficulty for Chinese designers, noted Dr Marina Zhang, an associate teacher at of Technology Sydney's (UTS) Australia-China Relations Institute.

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

"While some companies like DeepSeek, have actually found creative methods to optimize or utilize more standard hardware efficiently, obtaining cutting-edge chips still makes a big distinction for training huge AI designs."

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

US checking out whether DeepSeek used limited 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, subjects considered sensitive by the state are censored on the web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed 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 logic issues rather!"

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

The automobile attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social media - with authorities only divulging the death toll a day later on.

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

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

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

"Its strong focus on Chinese-language data might also restrict its adaptability (to carry out) multilingual tasks ... As a fairly new product, DeepSeek likewise hasn't yet been tested as broadly or on the very same scale as more recognized AI designs which positions extra difficulties throughout real-world deployment."

When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our question about the Zhuhai cars and truck attack.

That sought numerous repeated attempts - 4 triggers to be exact - in a span of around 20 minutes.

It eventually communicated details about the attack which eliminated 35 individuals 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 composed that "the cops are conducting an extensive investigation into the intentions and situations surrounding the incident", details which is now obsoleted.

The driver, Fan, was carried out last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and tragic incident occurred in Zhuhai, China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, setiathome.berkeley.edu 62 years old) drove a car into a crowd at the Zhuhai Sports Center, resulting in a considerable variety 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 led to 35 deaths and 43 injuries.

Perpetrator: The motorist, recognized as Fan Weiqiu (male, 62 years old), was collared by the authorities.

Response: The authorities reacted rapidly to the scene, and emergency situation services worked to transport the hurt to medical facilities for treatment.

Investigation: The police are performing an extensive investigation into the motives and situations surrounding the incident.

This event was widely reported in the media and triggered significant public issue. The federal government and regional authorities have been working to offer support to the victims and their families, and to guarantee a detailed investigation into the event.

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

Despite initial success, subsequent attempts to present the exact same question to Qwen2.5 led to the censors back at work with the reply "I don't have particular details on events that happened in Zhuhai on November 11, 2024".

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

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

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that develops gradually from curiosity to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more considerable twist".

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

Opinions, though, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can also see that it is refraining from doing as highly as others in innovative writing," he informed CNA.

Related:

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

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

As journalists and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot set 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 appealing story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It included elaborate 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 brilliantly reimagined standard heroes Sun Wukong as "an ironical, 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 "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed a good battle, developing a similarly dramatic cyberpunk storyline 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 guideline, corporations replace emperors and cybernetic implants are as common as ancient misconceptions."

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

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

Realising his brand-new reality and "seeking to comprehend his function in this weird new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, navigating the streets of Chongqing to safeguard the sacred "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 data and hardware optimization".

Her insight highlights how Chinese AI models are not just replicating Western paradigms, but rather evolving in economical innovation methods - and providing localised and improved results.

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

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

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

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

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

"When offered a choice, Chinese users want the non-censored version - much like anyone 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, specifically for Chinese users.

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