GitLab

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 startup DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is created 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 goal 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 been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for China Analysis.

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

But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized gamers like start-up firms might have functions to play in AI research and advancements, he adds.

'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 "emphasis on cost advantage" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference expenses - the expenses of using a trained design to reason from brand-new data.

2025 might likewise see the emergence of more Chinese AI designs dealing with innovative reasoning jobs.

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

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

Chinese AI companies are moving quickly, experts say, developing on DeepSeek's momentum to come up with their own ingenious and affordable ways to apply generative AI to jobs and establish more innovative items beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains an essential hurdle for Chinese designers, kept in mind Dr Marina Zhang, an associate teacher at University 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 model abilities," she said.

"While some companies like DeepSeek, have found imaginative methods to enhance or utilize more fundamental hardware efficiently, obtaining cutting-edge chips still makes a huge distinction for training really big AI models."

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

US checking out whether DeepSeek used 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 considered delicate by the state are censored on the internet so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are set to steer 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 reasoning issues rather!"

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

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

DeepSeek failed to point out that an attack had occurred, highlighting instead a military air program and other events that had happened in the city like songs' day shopping sales in addition to sports and cultural activities.

Dr Zhang thinks that it might 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 systems and has restricted access to advanced hardware which can affect how quickly and thoroughly the model can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language information may likewise limit its adaptability (to perform) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been evaluated as broadly or on the exact same scale as more recognized AI designs which poses additional obstacles throughout real-world implementation."

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

That was after numerous duplicated efforts - 4 prompts to be accurate - in a period of around 20 minutes.

It eventually communicated details about the attack which killed 35 individuals and left dozens of others hurt, larsaluarna.se 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 carrying out an extensive examination into the motives and scenarios surrounding the occurrence", details which is now dated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's response completely:

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

Date and Time: The incident took place on November 11, 2024, at approximately 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 old), was apprehended by the cops.

Response: The police reacted rapidly to the scene, and emergency services worked to transfer the hurt to healthcare facilities for treatment.

Investigation: The police are conducting an extensive examination into the intentions and scenarios surrounding the incident.

This event was commonly reported in the media and triggered considerable public concern. The government and local authorities have been working to provide assistance to the victims and their households, and to guarantee a detailed investigation into the occurrence.

If you need more detailed details or have particular questions about the occurrence, feel complimentary to ask.

Despite initial success, subsequent efforts to position the very same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on occasions that took place in Zhuhai on November 11, 2024".

The transformed reaction likewise raised questions about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had actually been extensively published in international news reports 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 provide structured and even "emotionally rich" writing.

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

"Qwen2.5 delivered a story that builds slowly from interest to seriousness, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more considerable twist".

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

Opinions, however, vary.

Chen thinks 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, 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, enjoyable 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 standard sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek came up with an appealing 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 elaborate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise remarkably reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed a good battle, coming up with a similarly remarkable 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 replace emperors and cybernetic implants are as common as ancient misconceptions."

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

"The motion picture starts with the awakening of Sun Wukong within a modern research center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "looking for to comprehend his function in this weird brand-new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "hard to make a conclusive declaration" about which bot was best, including that each showed its own strengths in different areas, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI designs are not simply duplicating Western paradigms, but rather developing in affordable innovation methods - and providing localised and enhanced results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual responses to concerns about Chinese existing occasions, which gives it an added advantage.

Experts likewise 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, creator and CEO of the research firm Strategy Risks.

"When given a choice, Chinese users desire the non-censored variation - much like anybody else, so I feel like that's a piece missing 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 percent of people utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other efficient methods," Chen said.