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 produced 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 objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "tactically important" and its venture into the field has actually been "years in the making", said Chen Qiheng, an associated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed pledges of real-world company applications, Chen told CNA.

But it was DeepSeek's increase that truly "encouraged" the concept that smaller 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 model as impactful as it claims?

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

The "focus on expense advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and - the costs of utilizing a trained model to draw conclusions from brand-new data.

2025 could likewise see the development of more Chinese AI designs dealing with advanced reasoning tasks.

"We could see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete methods to commercialise their models and integrate them with scientific research study," Chen included.

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

Chinese AI business are moving rapidly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to use generative AI to tasks and develop advanced items beyond chatbots.

But on the other side, systemcheck-wiki.de access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial difficulty for Chinese developers, noted 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 many to count on older or lower-performance alternatives which can slow training and lower model capabilities," she said.

"While some companies like DeepSeek, have discovered creative ways to optimize or utilize more fundamental hardware effectively, obtaining advanced chips still makes a huge difference for training really big AI models."

DeepSeek-Nvidia chips: Singapore states it anticipates companies to comply with 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, subjects deemed delicate by the state are censored on the internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell 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 logic issues rather!"

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

The cars and truck attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social networks - with authorities just revealing the death toll a day later on.

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

Dr Zhang thinks that it may be a mix of factors at play, such as censorship along with "a couple of useful constraints".

"DeepSeek depends on a mix of older graphics processing units and has actually limited access to innovative hardware which can impact how rapidly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data might likewise limit its adaptability (to perform) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the exact same scale as more established AI designs which postures extra difficulties during real-world implementation."

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

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

It ultimately relayed details about the attack which eliminated 35 people and left lots of others hurt, also 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 wrote that "the cops are performing a comprehensive examination into the motives and circumstances surrounding the incident", details which is now dated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's action in full:

Answer: On Nov 11, 2024, a significant and terrible incident happened in Zhuhai, China. According to numerous news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a significant variety of casualties. Here are the crucial details:

Date and Time: The event occurred 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 driver, recognized as Fan Weiqiu (male, trademarketclassifieds.com 62 years old), was nabbed by the authorities.

Response: The police reacted quickly to the scene, and emergency situation services worked to carry the hurt to hospitals for treatment.

Investigation: The police are conducting a comprehensive examination into the intentions and scenarios surrounding the event.

This occasion was widely reported in the media and triggered significant public concern. The federal government and local authorities have been working to offer assistance to the victims and their households, and to guarantee a detailed examination into the occurrence.

If you require more detailed details or have specific questions about the event, do not hesitate to ask.

Despite initial success, subsequent attempts to present the 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 transformed action likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been commonly released in worldwide news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that develops gradually from curiosity to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more substantial twist".

"DeepSeek wrote an excellent story but lacked tension and an impactful climax, making Qwen2.5 the obvious option."

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, however we can also see that it is refraining from doing as highly as others in imaginative 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 jolts global AI scene

As journalists and higgledy-piggledy.xyz authors, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore impressive, Journey to the West.

True to form, DeepSeek came up with an engaging story embeded in the year 2145 entitled, "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 likewise brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg club owner "drowning in debt 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, creating a similarly dramatic cyberpunk story 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 change emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a story that seemed more matched for an animation movie.

"The movie 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 new reality and "looking for to understand his function in this unusual new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

The trio then embarks on a mission, navigating the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not simply reproducing Western paradigms, however rather developing in affordable development methods - and providing localised and improved outcomes.

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 creative flair that produced a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

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

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

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

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