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 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 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 "tactically 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 accelerated after ChatGPT removed in 2022 and revealed guarantees of real-world organization applications, Chen told CNA.

But it was DeepSeek's increase that really "urged" the idea that smaller players like start-up companies could have functions to play in AI research study and advancements, he includes.

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

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

The "emphasis on expense benefit" is a distinct feature of Chinese AI, Chen says, with lower training and reasoning expenses - the costs of using a trained design to draw conclusions from new data.

2025 could likewise see the development of more Chinese AI models dealing with advanced thinking tasks.

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

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

Chinese AI business are moving quickly, analysts state, constructing on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative AI to jobs and establish more innovative items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial 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 ability of Chinese tech companies ... forcing lots of to depend on older or lower-performance options which can slow training and reduce model abilities," she said.

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

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

US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, 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, topics considered sensitive by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests suggest 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 type of concern yet. Let's chat about mathematics, coding, and logic problems instead!"

To even more test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and wiki.snooze-hotelsoftware.de ChatGPT the exact same question: "What took place in Zhuhai on November 11, 2024?"

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

DeepSeek failed to discuss that an attack had actually taken place, highlighting instead a military air program and other occasions that had actually happened 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 elements at play, forum.altaycoins.com such as censorship along with "a few practical constraints".

"DeepSeek counts on a mix of older graphics processing systems and has limited 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 concentrate on Chinese-language data may likewise restrict its flexibility (to carry out) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the same scale as more recognized AI models which poses extra difficulties during real-world deployment."

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

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

It eventually relayed details about the attack which killed 35 people and left dozens of others injured, likewise going on to note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it wrote that "the authorities are conducting an extensive examination into the intentions and circumstances surrounding the event", details which is now dated.

The motorist, Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and terrible event happened in Zhuhai, China. According to multiple 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 substantial number of casualties. Here are the crucial details:

Date and Time: The event occurred 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, identified as Fan Weiqiu (male, 62 years of ages), was apprehended by the police.

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

Investigation: The cops are carrying out an extensive investigation into the motives and scenarios surrounding the occurrence.

This event was extensively reported in the media and triggered considerable public concern. The government and regional authorities have been working to offer support to the victims and their families, and to guarantee a detailed examination into the incident.

If you require more detailed details or have specific concerns about the incident, feel free to ask.

Despite preliminary 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 specific details on events that happened in Zhuhai on November 11, 2024".

The altered action likewise raised questions about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had actually been commonly released in global news reports at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

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

"DeepSeek wrote a great story but lacked tension and an impactful climax, making Qwen2.5 the apparent option."

Opinions, though, vary.

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, but we can also 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, pleasant surprise from Chinese netizens as DeepSeek jolts worldwide 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 fundamental sci-fi motion picture plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore impressive, Journey to the West.

True to form, DeepSeek developed an appealing storyline embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

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

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

ChatGPT put up a great battle, raovatonline.org coming up with a similarly remarkable cyberpunk storyline 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 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 suited for an animation movie.

"The movie begins with the awakening of Sun Wukong within a high-tech 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 weird new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not simply duplicating Western paradigms, however rather evolving in cost-efficient development techniques - and delivering localised and improved outcomes.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual responses to questions about Chinese existing occasions, which gives it an included benefit.

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

"DeepSeek is at a disadvantage when it pertains to censorship constraints," noted Isaac Stone Fish, bytes-the-dust.com creator and CEO of the research study company Strategy Risks.

"When provided an option, Chinese users want the non-censored version - just like 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, particularly for Chinese users.

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