tiemao

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 created 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 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 financial investments in Chinese AI sped up after ChatGPT took off in 2022 and showed pledges of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that really "urged" the concept that smaller sized gamers like start-up firms could have functions to play in AI research study and developments, 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 company simply changed the rules of tech-geopolitics

The "emphasis on cost advantage" is a distinctive function of Chinese AI, Chen states, with lower training and reasoning costs - the expenses of utilizing a trained model to draw conclusions from brand-new information.

2025 might also see the introduction of more Chinese AI models taking on innovative reasoning tasks.

"We might see some AI companies concentrating on getting closer to synthetic basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with clinical research," Chen included.

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

Chinese AI companies are moving quickly, analysts say, building on DeepSeek's momentum to come up with their own ingenious and affordable methods to use generative AI to jobs and establish advanced items beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, raovatonline.org remains an essential obstacle for Chinese designers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the capability of Chinese tech companies ... requiring lots of to depend on older or lower-performance options which can slow training and lower model abilities," she said.

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

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

US checking out whether DeepSeek used restricted AI chips obtained through other nations, pediascape.science source says

So how do Chinese AI bots match up against ChatGPT? We put them to the test.

WHICH BEST EVENTS IN CHINA?

In China, topics deemed delicate by the state are censored on the web so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to avoid domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about math, coding, and logic issues rather!"

To further test for accuracy and self-censorship, it-viking.ch we asked DeepSeek-R1, Qwen2.5 and wiki.myamens.com ChatGPT the exact same concern: "What took place in Zhuhai on November 11, 2024?"

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

DeepSeek failed to point out that an attack had happened, highlighting rather a military air show and other occasions that had actually taken place in the city like singles' 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 in addition to "a few useful constraints".

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

"Its strong focus on Chinese-language information might likewise limit its flexibility (to perform) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been evaluated as broadly or on the same scale as more recognized AI models which presents extra obstacles during real-world release."

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

That wanted numerous repeated efforts - four triggers to be accurate - in a period of around 20 minutes.

It ultimately relayed details about the attack which eliminated 35 individuals and left lots 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 motives and circumstances surrounding the event", details which is now outdated.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's action in complete:

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

Date and Time: The occurrence occurred on November 11, 2024, at approximately 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: higgledy-piggledy.xyz The attack led to 35 deaths and 43 injuries.

Perpetrator: The motorist, determined as Fan Weiqiu (male, 62 years of ages), was nabbed by the police.

Response: The police responded rapidly to the scene, and emergency situation services worked to carry the injured to health centers for treatment.

Investigation: The police are conducting a comprehensive examination into the intentions and circumstances surrounding the incident.

This event was extensively reported in the media and triggered substantial public issue. The federal government and regional authorities have been working to supply assistance to the victims and their households, and to make sure a detailed examination into the occurrence.

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

Despite initial success, subsequent attempts to pose the very same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on events that happened in Zhuhai on November 11, 2024".

The altered response also raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had been extensively released in worldwide news reports at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the capability of Chinese AI apps to deliver 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," wrote tech writer 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 unforeseen and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more substantial twist".

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

Opinions, though, vary.

Chen thinks 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 also see that it is refraining from doing as strongly as others in innovative 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 shocks international 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 film plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek came up with an engaging storyline embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It included 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 brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen fight body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT put up an excellent battle, coming up with a similarly significant cyberpunk story which likewise 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 typical as ancient misconceptions."

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

"The movie begins with the awakening of Sun Wukong within a modern research facility 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 purpose in this unusual brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then starts a quest, navigating the streets of Chongqing to secure 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, adding that each displayed its own strengths in various locations, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI models are not simply duplicating Western paradigms, however rather evolving in economical development approaches - and delivering 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 engaging and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers precise and factual responses to concerns about Chinese present occasions, which offers it an included advantage.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and engel-und-waisen.de CEO of the research study firm Strategy Risks.

"When given an option, Chinese users desire the non-censored version - similar to anyone 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, especially for Chinese users.

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