setech

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 produced 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 objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "tactically important" and its venture into the field has been "years in the making", said Chen Qiheng, an affiliated 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 showed pledges of real-world company applications, Chen told CNA.

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

'A lot is up in the air': Is Chinese firm DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI company simply changed the rules of tech-geopolitics

The "focus on expense advantage" is an unique feature of Chinese AI, Chen states, with lower training and inference costs - the costs of using a trained model to reason from brand-new data.

2025 could also see the introduction of more Chinese AI models tackling advanced reasoning jobs.

"We might see some AI firms concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate 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 business are moving rapidly, experts say, developing 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 side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a crucial obstacle 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 companies ... requiring lots of to rely on older or lower-performance options which can slow training and minimize model capabilities," she said.

"While some companies like DeepSeek, have found innovative ways to enhance or use more basic hardware efficiently, obtaining advanced chips still makes a big difference for training large AI designs."

DeepSeek-Nvidia chips: Singapore says it expects business to comply with its laws

US looking into whether DeepSeek utilized 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, topics deemed sensitive by the state are censored on the internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what took place in Tiananmen Square in 1989.

Tests suggest 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 question yet. Let's chat about math, coding, and reasoning problems rather!"

To further check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What happened in Zhuhai on November 11, 2024?"

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

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

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

"DeepSeek relies on a mix of older graphics processing units and has limited access to advanced hardware which can impact how quickly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language information may also limit its flexibility (to carry out) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been checked as broadly or on the very same scale as more established AI designs which poses additional challenges throughout real-world implementation."

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

That sought several repeated attempts - four prompts to be exact - in a period of around 20 minutes.

It eventually relayed details about the attack which eliminated 35 people and left dozens of others injured, 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 authorities are conducting an extensive investigation into the motives and scenarios surrounding the incident", demo.qkseo.in details which is now dated.

The motorist, Fan, was carried out last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a major and terrible incident occurred in Zhuhai, China. According to numerous news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a substantial variety of casualties. Here are the essential details:

Date and Time: The occurrence took place on November 11, 2024, at roughly 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 chauffeur, determined as Fan Weiqiu (male, 62 years old), was collared by the authorities.

Response: The police reacted rapidly to the scene, and emergency services worked to carry the injured to medical facilities for treatment.

Investigation: The authorities are conducting an extensive examination into the intentions and circumstances surrounding the occurrence.

This occasion was widely reported in the media and caused considerable public concern. The federal government and local authorities have actually been working to supply support to the victims and their households, and to ensure a detailed investigation into the incident.

If you need more detailed details or have particular concerns about the occurrence, do not hesitate to ask.

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

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

Predictably, public details that had actually been widely released in worldwide report at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that constructs slowly from interest to urgency, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more considerable twist".

"DeepSeek composed a great story however lacked stress and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, vary.

Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to creative 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 creative writing," he informed 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 jolts international AI scene

As journalists and writers, we had to see this for systemcheck-wiki.de ourselves so we put each bot to the test - to come up with a fundamental sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore impressive, Journey to the West.

True to form, engel-und-waisen.de DeepSeek came up with an appealing storyline set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It included sophisticated settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, 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, developing a similarly remarkable cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities rule, corporations change emperors and cybernetic implants are as typical as ancient misconceptions."

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

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

Realising his new truth and "seeking to understand his function in this strange 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 mission, browsing the streets of Chongqing to safeguard 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 definitive statement" about which bot was best, including that each showed its own strengths in various 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 cost-effective innovation techniques - and providing localised and improved outcomes.

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

DeepSeek's sci-fi film plot showed its creative flair that produced 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, supplies precise and factual actions to concerns about Chinese present events, which provides it an added benefit.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research study firm Strategy Risks.

"When offered a choice, Chinese users desire the non-censored version - similar to anyone else, so I seem like that's a piece missing out on from it."

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

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