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 actually 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 essential" and its foray into the field has actually 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 Chinese AI accelerated after ChatGPT took off in 2022 and revealed promises of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that truly "urged" the concept that smaller sized gamers like start-up firms could have roles 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 business just altered the rules of tech-geopolitics

The "focus on cost advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of utilizing a trained model to reason from brand-new information.

2025 could also see the emergence of more Chinese AI designs taking on sophisticated thinking tasks.

"We could see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete ways to commercialise their models and integrate them with clinical research study," Chen added.

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

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

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a key difficulty for Chinese developers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the ability of Chinese tech business ... forcing many to depend on older or lower-performance alternatives which can slow training and minimize model abilities," she said.

"While some business like DeepSeek, have actually found imaginative ways to enhance or utilize more standard hardware efficiently, obtaining cutting-edge chips still makes a big difference for training huge AI designs."

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

US looking into whether DeepSeek utilized limited AI chips obtained through other nations, source says

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 deemed delicate by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are set to avoid 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 mathematics, coding, and reasoning issues rather!"

To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "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 heavily censored on Chinese social networks - with authorities just divulging the death toll a day later on.

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

Dr Zhang thinks that it might be a mix of aspects at play, such as censorship along with "a couple of practical constraints".

"DeepSeek counts on a mix of older graphics processing systems and has actually limited access to innovative hardware which can affect how rapidly and extensively the model can be trained or upgraded," she said, pointing to 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 brand-new item, DeepSeek also hasn't yet been evaluated as broadly or on the exact same scale as more established AI designs which poses extra difficulties throughout real-world implementation."

When it pertained to Qwen2.5, larsaluarna.se Alibaba's chatbot surprisingly answered our concern about the Zhuhai car attack.

That sought numerous duplicated attempts - 4 prompts to be precise - in a period of around 20 minutes.

It eventually passed on details about the attack which killed 35 people 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 police are conducting a thorough examination into the intentions and circumstances surrounding the occurrence", details which is now outdated.

The motorist, Fan, wiki.myamens.com was executed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a major and terrible occurrence occurred in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the key details:

Date and Time: The event occurred on November 11, 2024, at roughly 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 chauffeur, recognized as Fan Weiqiu (male, 62 years of ages), was captured by the authorities.

Response: The authorities reacted quickly to the scene, and emergency services worked to transport the injured to medical facilities for wavedream.wiki treatment.

Investigation: gratisafhalen.be The authorities are conducting a thorough investigation into the intentions and situations surrounding the occurrence.

This event was widely reported in the media and caused considerable public concern. The government and local authorities have actually 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 concerns about the event, do not hesitate to ask.

Despite initial success, subsequent efforts to position the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that happened in Zhuhai on November 11, 2024".

The transformed action likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had actually been extensively released in worldwide news reports at the time of the mishap - 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 abundant" writing.

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

"Qwen2.5 delivered a story that develops gradually from interest to seriousness, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more substantial twist".

"DeepSeek composed a good story but did not have stress and an impactful climax, making Qwen2.5 the obvious option."

Opinions, however, vary.

Chen thinks that Qwen2.5 does not carry out 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 likewise see that it is refraining from doing as strongly as others in creative writing," he told CNA.

Related:

China's new face of AI: Who is DeepSeek founder Liang Wenfeng?

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks international 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 standard sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore legendary, 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 consisted of intricate 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 "a sarcastic, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg club owner "drowning in financial obligation and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up an excellent battle, developing a similarly remarkable cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities guideline, corporations replace emperors and cybernetic implants are as common as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a storyline that seemed more fit for an animation film.

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

Realising his brand-new truth and "looking for to understand his function in this odd brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to protect the sacred "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI designs are not merely reproducing Western paradigms, but rather developing in affordable development approaches - and providing localised and improved results.

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 innovative flair that made for a more engaging and creative story as compared to Qwen2.5 and ChatGPT's efforts.

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

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," noted Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.

"When given a choice, Chinese users want the non-censored version - similar to anybody else, so I feel 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, particularly for Chinese users.

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