I Tested DeepSeek’s R1 and V3 Coding Skills – and we’re not All Doomed (Yet).

DeepSeek blew up into the world’s awareness this past weekend. It sticks out for 3 effective reasons:

1. It’s an AI chatbot from China, instead of the US

2. It’s open source.

3. It uses vastly less infrastructure than the big AI tools we have actually been taking a look at.

Also: Apple researchers expose the secret sauce behind DeepSeek AI

Given the US government’s concerns over TikTok and possible Chinese federal government participation in that code, a new AI emerging from China is bound to produce attention. ZDNET’s Radhika Rajkumar did a deep dive into those problems in her short article Why China’s DeepSeek could rupture our AI bubble.

In this post, we’re preventing politics. Instead, I’m putting both DeepSeek V3 and DeekSeek R1 through the exact same set of AI coding tests I’ve thrown at 10 other large language models. According to DeepSeek itself:

Choose V3 for tasks requiring depth and accuracy (e.g., fixing innovative mathematics issues, generating intricate code).

Choose R1 for latency-sensitive, high-volume applications (e.g., consumer support automation, basic text processing).

You can select in between R1 and V3 by clicking the little button in the chat user interface. If the button is blue, you’re using R1.

The brief response is this: impressive, however clearly not ideal. Let’s dig in.

Test 1: Writing a WordPress plugin

This test was actually my very first test of ChatGPT’s shows prowess, method back in the day. My spouse required a plugin for WordPress that would assist her run a participation device for her online group.

Also: The very best AI for coding in 2025 (and what not to use)

Her needs were fairly simple. It required to take in a list of names, one name per line. It then had to arrange the names, and if there were duplicate names, different them so they weren’t noted side-by-side.

I didn’t truly have time to code it for her, so I decided to give the AI the obstacle on an impulse. To my big surprise, it worked.

Since then, it’s been my first test for AIs when assessing their programming abilities. It needs the AI to know how to set up code for the WordPress framework and follow prompts clearly sufficient to create both the user interface and program logic.

Only about half of the AIs I’ve evaluated can completely pass this test. Now, nevertheless, we can add one more to the winner’s circle.

DeepSeek V3 created both the user interface and program reasoning exactly as defined. When It Comes To DeepSeek R1, well that’s an intriguing case. The « thinking » element of R1 caused the AI to spit out 4502 words of analysis before sharing the code.

The UI looked different, with much larger input areas. However, both the UI and reasoning worked, so R1 also passes this test.

So far, DeepSeek V3 and R1 both passed one of four tests.

Test 2: Rewriting a string function

A user grumbled that he was not able to get in dollars and cents into a donation entry field. As composed, my code only allowed dollars. So, the test includes giving the AI the regular that I wrote and asking it to rewrite it to permit both dollars and cents

Also: My preferred ChatGPT function simply got way more effective

Usually, this results in the AI generating some regular expression validation code. DeepSeek did generate code that works, although there is space for improvement. The code that DeepSeek V2 wrote was needlessly long and repetitious while the thinking before producing the code in R1 was also long.

My greatest concern is that both models of the DeepSeek validation guarantees recognition as much as 2 decimal locations, however if an extremely large number is entered (like 0.30000000000000004), making use of parseFloat does not have explicit rounding knowledge. The R1 model also used JavaScript’s Number conversion without looking for edge case inputs. If bad data returns from an earlier part of the regular expression or a non-string makes it into that conversion, the code would crash.

It’s odd, since R1 did present a really nice list of tests to confirm versus:

So here, we have a split choice. I’m offering the point to DeepSeek V3 due to the fact that neither of these issues its code produced would trigger the program to break when run by a user and would create the expected results. On the other hand, I need to provide a stop working to R1 due to the fact that if something that’s not a string somehow gets into the Number function, a crash will take place.

And that provides DeepSeek V3 2 triumphes of 4, but DeepSeek R1 only one triumph of four up until now.

Test 3: Finding an irritating bug

This is a test produced when I had an extremely bothersome bug that I had trouble locating. Once once again, I decided to see if ChatGPT could handle it, which it did.

The difficulty is that the answer isn’t obvious. Actually, the obstacle is that there is an obvious response, based on the mistake message. But the apparent answer is the incorrect answer. This not just caught me, but it regularly catches some of the AIs.

Also: Are ChatGPT Plus or Pro worth it? Here’s how they compare to the totally free variation

Solving this bug requires understanding how particular API calls within WordPress work, being able to see beyond the error message to the code itself, and then understanding where to find the bug.

Both DeepSeek V3 and R1 passed this one with nearly identical responses, bringing us to three out of four wins for V3 and 2 out of 4 wins for R1. That currently puts DeepSeek ahead of Gemini, Copilot, Claude, and Meta.

Will DeepSeek score a crowning achievement for V3? Let’s discover out.

Test 4: Writing a script

And another one bites the dust. This is a difficult test since it needs the AI to comprehend the interaction between three environments: AppleScript, the Chrome things design, and a Mac scripting tool called Keyboard Maestro.

I would have called this an unjust test due to the fact that Keyboard Maestro is not a traditional programming tool. But ChatGPT managed the test easily, understanding exactly what part of the issue is managed by each tool.

Also: How ChatGPT scanned 170k lines of code in seconds, saving me hours of work

Unfortunately, neither DeepSeek V3 or R1 had this level of knowledge. Neither model knew that it required to divide the task in between directions to Keyboard Maestro and Chrome. It also had relatively weak knowledge of AppleScript, writing customized routines for AppleScript that are native to the language.

Weirdly, the R1 design failed also since it made a bunch of inaccurate assumptions. It presumed that a front window constantly exists, which is certainly not the case. It likewise made the presumption that the presently front running program would always be Chrome, instead of clearly inspecting to see if Chrome was running.

This leaves DeepSeek V3 with 3 correct tests and one fail and DeepSeek R1 with 2 right tests and 2 fails.

Final thoughts

I found that DeepSeek’s persistence on utilizing a public cloud e-mail address like gmail.com (rather than my normal e-mail address with my corporate domain) was irritating. It also had a variety of responsiveness stops working that made doing these tests take longer than I would have liked.

Also: How to use ChatGPT to compose code: What it does well and what it does not

I wasn’t sure I ‘d be able to compose this short article due to the fact that, for the majority of the day, I got this error when attempting to sign up:

DeepSeek’s online services have recently faced large-scale malicious attacks. To ensure ongoing service, registration is momentarily limited to +86 telephone number. Existing users can visit as typical. Thanks for your understanding and support.

Then, I got in and had the ability to run the tests.

DeepSeek seems to be extremely chatty in terms of the code it creates. The AppleScript code in Test 4 was both incorrect and exceedingly long. The regular expression code in Test 2 was right in V3, however it might have been written in a manner in which made it much more maintainable. It failed in R1.

Also: If ChatGPT produces AI-generated code for your app, who does it actually come from?

I’m definitely impressed that DeepSeek V3 vanquished Gemini, Copilot, and Meta. But it seems at the old GPT-3.5 level, which indicates there’s certainly room for improvement. I was dissatisfied with the results for the R1 model. Given the choice, I ‘d still pick ChatGPT as my programming code assistant.

That stated, for a new tool working on much lower infrastructure than the other tools, this might be an AI to view.

What do you believe? Have you attempted DeepSeek? Are you utilizing any AIs for shows support? Let us know in the below.

You can follow my day-to-day job updates on social networks. Make certain to sign up for my weekly update newsletter, and follow me on Twitter/X at @DavidGewirtz, on Facebook at Facebook.com/ DavidGewirtz, on Instagram at Instagram.com/ DavidGewirtz, on Bluesky at @DavidGewirtz. com, and on YouTube at YouTube.com/ DavidGewirtzTV.