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 created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "tactically crucial" and its foray 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 wiki.asexuality.org public investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed promises of real-world service applications, Chen told CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller players like start-up companies could have roles to play in AI research study and advancements, he includes.

'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 just altered the guidelines of tech-geopolitics

The "emphasis on cost benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning expenses - the expenses of utilizing a trained model to draw conclusions from brand-new data.

2025 might likewise see the emergence of more Chinese AI models taking on advanced reasoning tasks.

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

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

Chinese AI business are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own innovative and economical ways to apply generative AI to jobs and develop more innovative items beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a key obstacle 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 companies ... forcing lots of to rely on older or lower-performance options which can slow training and minimize design abilities," she said.

"While some companies like DeepSeek, have discovered creative ways to optimize or utilize more basic hardware efficiently, obtaining innovative chips still makes a huge distinction for training huge AI models."

DeepSeek-Nvidia chips: Singapore states it expects business to abide by its laws

US checking out whether DeepSeek used limited 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 internet so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed to steer clear of 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 test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "What took place in Zhuhai on November 11, 2024?"

The cars and truck attack outside a sports stadium 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 taken place, highlighting rather a military air program and other occasions that had actually taken place in the city like songs' day shopping sales in addition to sports and cultural activities.

Dr Zhang thinks that it may be a mix of elements at play, such as censorship along with "a few practical constraints".

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

"Its strong focus on Chinese-language information may likewise restrict its adaptability (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the exact same scale as more established AI models which poses additional obstacles during real-world implementation."

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

That wanted numerous repeated efforts - 4 triggers to be precise - in a period of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 people and left dozens of others injured, likewise going on to list details like the date and time, about the assailant including his name and age, in addition to casualties.

However, it wrote that "the cops are carrying out an extensive investigation into the intentions and scenarios surrounding the occurrence", details which is now obsoleted.

The motorist, Fan, was performed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and awful event took place in Zhuhai, China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a considerable number of casualties. Here are the key details:

Date and Time: The incident happened 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 motorist, identified as Fan Weiqiu (male, 62 years old), was collared by the authorities.

Response: The police reacted quickly to the scene, and emergency situation services worked to carry the injured to healthcare facilities for treatment.

Investigation: The authorities are performing an extensive investigation into the intentions and hb9lc.org circumstances surrounding the occurrence.

This event was commonly reported in the media and triggered significant public concern. The federal government and local authorities have actually been working to offer support to the victims and their families, and to make sure a detailed examination into the occurrence.

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

Despite initial success, subsequent efforts to posture the same concern to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on occasions that happened in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT cited public details that had been extensively released in international news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the capability of Chinese AI apps to deliver structured and even "mentally abundant" writing.

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

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

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

Opinions, however, differ.

Chen thinks that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to innovative 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 informed CNA.

Related:

China's brand-new face of AI: Who is DeepSeek creator Liang Wenfeng?

'Made in China': pipewiki.org Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks worldwide AI scene

As reporters and writers, 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, featuring main characters from the classic Chinese folklore legendary, Journey to the West.

True to form, DeepSeek developed 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 elaborate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg bar 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 set up a good fight, systemcheck-wiki.de creating an equally remarkable 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 guideline, corporations change emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this difficulty - providing a storyline that appeared more suited for an animation movie.

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

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

The trio then embarks on a mission, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "difficult to make a definitive declaration" about which bot was best, including that each displayed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not simply replicating Western paradigms, however rather developing in cost-efficient innovation methods - and delivering localised and enhanced outcomes.

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

DeepSeek's sci-fi motion picture plot demonstrated its imaginative flair that produced a more interesting and imaginative narrative as compared to Qwen2.5 and surgiteams.com ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual responses to questions about Chinese existing events, which offers it an included benefit.

Experts likewise weighed in on their ideas after utilizing 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 variation - much like anybody else, so I seem like that's a piece missing from it."

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

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