arcbjorn

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 generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has 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 important" and its venture 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 investments in Chinese AI accelerated after ChatGPT removed in 2022 and showed guarantees of real-world organization applications, Chen told CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized players like start-up firms might 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 design as impactful as it claims?

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

The "emphasis on expense benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of using a trained model to reason from new information.

2025 might likewise see the emergence of more Chinese AI models dealing with innovative reasoning jobs.

"We might see some AI companies focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and incorporate them with clinical research study," Chen added.

AGI refers to a system with intelligence on par with human capabilities.

Chinese AI companies are moving quickly, analysts state, constructing on DeepSeek's momentum to come up with their own ingenious and affordable methods to use generative AI to tasks and establish advanced products beyond chatbots.

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

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

"While some business like DeepSeek, have actually found innovative methods to enhance or use more standard hardware efficiently, obtaining advanced chips still makes a huge difference for training huge AI models."

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

US looking into whether DeepSeek utilized limited 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, subjects deemed delicate by the state are censored on the web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what took place 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 math, coding, and logic problems rather!"

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

The car attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social media - with authorities just divulging the death toll a day later.

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

Dr Zhang believes that it may be a mix of factors at play, such as censorship in addition to "a few useful constraints".

"DeepSeek counts on a mix of older graphics processing systems and has actually limited access to advanced hardware which can impact how rapidly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language information might also restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more recognized AI designs which postures extra challenges throughout real-world deployment."

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

That sought several duplicated efforts - 4 prompts to be exact - in a span of around 20 minutes.

It ultimately relayed details about the attack which eliminated 35 people and left lots of others injured, also going on to list 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 a thorough investigation into the motives and situations surrounding the occurrence", details which is now dated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's reaction in full:

Answer: On Nov 11, 2024, a major and tragic occurrence occurred in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a substantial variety of casualties. Here are the crucial details:

Date and Time: pipewiki.org The event happened on November 11, 2024, at around 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 motorist, determined as Fan Weiqiu (male, 62 years old), was apprehended by the police.

Response: The police responded rapidly to the scene, and emergency situation services worked to transfer the hurt to hospitals for treatment.

Investigation: The cops are performing an extensive examination into the intentions and circumstances surrounding the incident.

This occasion was commonly reported in the media and caused considerable public issue. The government and regional authorities have been working to offer assistance to the victims and their families, and to ensure a detailed examination into the event.

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

Despite preliminary success, subsequent efforts to present the exact same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on events that occurred in Zhuhai on November 11, 2024".

The modified reaction also raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had actually been commonly released in international news reports 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 abundant" writing.

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

"Qwen2.5 delivered a story that builds gradually from curiosity to urgency, keeping the reader engaged. It uses an unanticipated 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, emotionally abundant story with a more considerable twist".

"DeepSeek wrote an excellent story however did not have tension and an impactful climax, making Qwen2.5 the evident choice."

Opinions, setiathome.berkeley.edu however, vary.

Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to imaginative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as highly as others in imaginative writing," he told CNA.

Related:

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

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

As reporters and authors, we had 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, featuring main characters from the timeless Chinese folklore legendary, Journey to the West.

True to form, DeepSeek developed an interesting storyline set 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 float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and forum.altaycoins.com Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up an excellent battle, creating a similarly dramatic cyberpunk story 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 guideline, corporations change emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, larsaluarna.se Qwen2.5 fell short in this challenge - providing a storyline that seemed more suited for an animation movie.

"The motion picture begins with the awakening of Sun Wukong within a modern research center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his new truth and "seeking to understand his purpose in this odd brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI designs are not just reproducing Western paradigms, but rather progressing in cost-effective innovation approaches - and providing localised and improved outcomes.

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

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

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

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

"DeepSeek is at a disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.

"When provided an option, Chinese users desire the non-censored variation - much 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, especially for Chinese users.

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