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 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 long been President Xi Jinping's goal and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically essential" 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 took off in 2022 and showed pledges of real-world business applications, wiki-tb-service.com Chen informed CNA.

But it was DeepSeek's rise that really "encouraged" the idea that smaller players like start-up companies might have roles to play in AI research 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 simply changed the guidelines of tech-geopolitics

The "emphasis on expense benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference costs - the costs of using a trained design to draw conclusions from brand-new information.

2025 might also see the introduction of more Chinese AI designs tackling innovative reasoning tasks.

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

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

Chinese AI business are moving quickly, experts state, building on DeepSeek's momentum to come up with their own ingenious and cost-efficient ways to apply generative AI to jobs and develop more sophisticated products beyond chatbots.

But on the other side, surgiteams.com access to high-end hardware, especially Nvidia's sophisticated AI chips, remains an essential hurdle 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) restrict the ability of Chinese tech companies ... forcing lots of to count on older or lower-performance alternatives which can slow training and reduce model abilities," she said.

"While some business like DeepSeek, have actually discovered innovative ways to optimize or use more standard hardware efficiently, obtaining innovative chips still makes a huge difference for training really big AI models."

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

US checking out whether DeepSeek utilized restricted 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, topics considered delicate by the state are censored on the web so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell 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 evaluate for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: "What took place in Zhuhai on November 11, 2024?"

The cars and truck 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.

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

Dr Zhang believes that it may be a mix of aspects at play, such as censorship as well as "a couple of practical constraints".

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

"Its strong focus on Chinese-language information may likewise limit its versatility (to perform) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been evaluated as broadly or on the same scale as more established AI models which positions extra challenges throughout real-world release."

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

That wanted several repeated attempts - four prompts to be accurate - 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 list details like the date and time, details about the assailant including his name and age, along with casualties.

However, it wrote that "the cops are conducting a thorough investigation into the intentions and circumstances surrounding the incident", details which is now obsoleted.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's action in full:

Answer: On Nov 11, 2024, a major and awful incident happened in Zhuhai, China. According to several news sources, archmageriseswiki.com a male called Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a substantial variety of casualties. Here are the key details:

Date and Time: The occurrence occurred 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, determined as Fan Weiqiu (male, 62 years of ages), was captured by the authorities.

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

Investigation: The cops are conducting a comprehensive investigation into the motives and circumstances surrounding the incident.

This occasion was widely reported in the media and caused considerable public issue. The government and regional authorities have been working to offer support to the victims and their households, and to make sure a detailed examination into the incident.

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

Despite preliminary success, subsequent efforts to present the same question to Qwen2.5 led to the censors back at work with the reply "I don't have specific details on events that occurred in Zhuhai on November 11, 2024".

The altered reaction likewise raised questions about its consistency and dependability.

Predictably, ChatGPT cited public details that had actually been widely published in international report at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 used a story with a more reflective 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 develops gradually from curiosity to seriousness, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more considerable twist".

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

Opinions, though, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise see that it is refraining from doing as strongly as others in innovative writing," he informed 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 journalists and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore legendary, Journey to the West.

True to form, DeepSeek came up with an interesting storyline 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 high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken battle body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT put up a good battle, creating an equally significant cyberpunk storyline which likewise 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 challenge - delivering a story that appeared more fit for an animation movie.

"The film begins with the awakening of Sun Wukong within a modern research facility located in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new reality and "seeking to understand his function in this unusual new world", he then escapes and larsaluarna.se fulfills Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard 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 models are not merely reproducing Western paradigms, but rather developing in cost-efficient development approaches - and providing localised and enhanced results.

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

DeepSeek's sci-fi movie plot showed its creative flair that made for a more appealing and higgledy-piggledy.xyz imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, genbecle.com unburdened by Chinese censorship constraints, provides precise and accurate reactions to concerns about Chinese current events, 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 downside when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and CEO of the research company Strategy Risks.

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

Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, links.gtanet.com.br specifically for Chinese users.

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