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 lags 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 venture into the field has 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 sped up after ChatGPT took off in 2022 and showed pledges of real-world service applications, Chen told CNA.

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

'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 changed the guidelines of tech-geopolitics

The "focus on cost benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference expenses - the costs of using a trained model to draw conclusions from brand-new information.

2025 could also see the development of more Chinese AI models taking on advanced reasoning jobs.

"We might see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and incorporate them with clinical research," Chen included.

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

Chinese AI companies are moving quickly, analysts say, building on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to use generative AI to jobs and establish more advanced products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a crucial difficulty for wavedream.wiki 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 capability of Chinese tech companies ... requiring numerous to rely on older or lower-performance options which can slow training and lower design capabilities," she said.

"While some business like DeepSeek, have actually found innovative methods to optimize or utilize more fundamental hardware efficiently, obtaining cutting-edge chips still makes a huge difference for training huge AI designs."

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

US checking out whether DeepSeek used restricted AI chips obtained through other nations, 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 considered sensitive by the state are censored on the internet so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are set to stay away from .

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about math, coding, and reasoning problems rather!"

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

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

DeepSeek failed to point out that an attack had happened, highlighting rather a military air program and other events that had happened 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 factors at play, such as censorship along with "a couple of useful constraints".

"DeepSeek depends on a mix of older graphics processing units and has actually restricted access to advanced hardware which can affect how rapidly and extensively the design can be trained or upgraded," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language information might also restrict its adaptability (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more recognized AI models which positions additional difficulties throughout real-world deployment."

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

That was after numerous repeated attempts - 4 prompts to be precise - in a period of around 20 minutes.

It eventually communicated details about the attack which eliminated 35 people and left lots of others injured, likewise 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 cops are conducting an extensive investigation into the motives and situations surrounding the occurrence", details which is now dated.

The motorist, yewiki.org Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and awful event took place in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the key details:

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

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

Investigation: The cops are performing a thorough examination into the intentions and situations surrounding the occurrence.

This occasion was extensively reported in the media and triggered significant public concern. The federal government and local authorities have actually been working to supply assistance to the victims and their families, and to guarantee a detailed investigation into the incident.

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

Despite preliminary success, pipewiki.org subsequent efforts to position the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on events that occurred in Zhuhai on November 11, 2024".

The transformed response also raised questions about its consistency and reliability.

Predictably, ChatGPT cited public details that had been commonly released in global 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 provide structured and even "emotionally abundant" writing.

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

"Qwen2.5 delivered a story that constructs gradually from curiosity 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, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more considerable twist".

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

Opinions, though, trademarketclassifieds.com vary.

Chen believes that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to imaginative 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 imaginative writing," he informed 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, systemcheck-wiki.de we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi film plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore epic, Journey to the West.

True to form, DeepSeek created an interesting story set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It included intricate 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 likewise brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg bar owner "drowning in financial obligation 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 good fight, developing a similarly remarkable cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".

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

Disappointingly, Qwen2.5 fell short in this obstacle - delivering a story that appeared more suited for an animation movie.

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

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

The trio then embarks on a mission, browsing the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard to make a conclusive statement" about which bot was best, including that each showed its own strengths in different locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI designs are not just reproducing Western paradigms, but rather developing in affordable development methods - and providing localised and enhanced outcomes.

In our tests, bytes-the-dust.com each bot showcased their own special strengths, which certainly made direct contrasts challenging.

DeepSeek's sci-fi film plot showed its innovative flair that made for a more appealing and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate responses to concerns about Chinese present events, which gives it an added benefit.

Experts also weighed in on their thoughts after using 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 offered an option, Chinese users desire the non-censored variation - much like 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, particularly for Chinese users.

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