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

DeepSeek took off into the world’s consciousness this previous weekend. It stands out for 3 powerful factors:

1. It’s an AI chatbot from China, rather than the US

2. It’s open source.

3. It uses greatly less infrastructure than the big AI tools we have actually been looking at.

Also: Apple scientists reveal the secret sauce behind DeepSeek AI

Given the US government’s concerns over TikTok and possible Chinese federal government involvement in that code, a brand-new AI emerging from China is bound to generate attention. ZDNET’s Radhika Rajkumar did a deep dive into those concerns in her article Why China’s DeepSeek might break our AI bubble.

In this post, we’re avoiding 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 jobs requiring depth and precision (e.g., resolving innovative math issues, creating complicated code).

Choose R1 for latency-sensitive, high-volume applications (e.g., customer assistance automation, standard text processing).

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

The short answer is this: remarkable, however clearly not ideal. Let’s dig in.

Test 1: Writing a WordPress plugin

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

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

Her needs were relatively basic. 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, separate them so they weren’t noted side-by-side.

I didn’t really have time to code it for her, so I decided to provide the AI the obstacle on a whim. To my huge surprise, it worked.

Since then, it’s been my very first test for AIs when assessing their programs skills. It needs the AI to know how to set up code for the WordPress structure and follow prompts plainly adequate to develop both the interface and program logic.

Only about half of the AIs I’ve tested can completely pass this test. Now, however, we can include another to the winner’s circle.

DeepSeek V3 developed both the interface and program reasoning exactly as defined. When It Comes To DeepSeek R1, well that’s an intriguing case. The “reasoning” element of R1 triggered the AI to spit out 4502 words of analysis before sharing the code.

The UI looked various, with much larger input areas. However, both the UI and reasoning worked, so R1 likewise 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 involves providing the AI the routine that I wrote and asking it to rewrite it to allow for both dollars and cents

Also: My preferred ChatGPT feature just got method more powerful

Usually, this results in the AI creating some regular expression recognition code. DeepSeek did produce code that works, although there is space for improvement. The code that DeepSeek V2 wrote was unnecessarily long and repetitive while the reasoning before creating the code in R1 was likewise long.

My most significant issue is that both models of the DeepSeek validation ensures recognition as much as 2 decimal places, however if a large number is gone into (like 0.30000000000000004), making use of parseFloat doesn’t have explicit rounding knowledge. The R1 model also utilized JavaScript’s Number conversion without inspecting for edge case inputs. If bad information returns from an earlier part of the routine expression or a non-string makes it into that conversion, the code would crash.

It’s odd, because R1 did present a really great 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 concerns its code produced would cause the program to break when run by a user and would create the expected results. On the other hand, I have to give a fail to R1 due to the fact that if something that’s not a string in some way enters the Number function, a crash will take place.

And that gives DeepSeek V3 2 triumphes of 4, however DeepSeek R1 just one triumph of four up until now.

Test 3: Finding an irritating bug

This is a test produced when I had a very annoying bug that I had trouble tracking down. Once again, I chose to see if ChatGPT could manage it, which it did.

The challenge is that the answer isn’t apparent. Actually, the difficulty is that there is an obvious response, based upon the error message. But the obvious answer is the incorrect response. This not just captured me, however it frequently catches some of the AIs.

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

Solving this bug requires comprehending how specific API calls within WordPress work, being able to see beyond the mistake message to the code itself, and then understanding where to discover the bug.

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

Will DeepSeek score a home run for V3? Let’s discover.

Test 4: Writing a script

And another one bites the dust. This is a challenging test due to the fact that it needs the AI to comprehend the interplay in between three environments: AppleScript, the Chrome object model, and a Mac scripting tool called Keyboard Maestro.

I would have called this an unjust test because Keyboard Maestro is not a traditional programs tool. But ChatGPT managed the test easily, comprehending precisely what part of the problem is dealt with by each tool.

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

Unfortunately, neither DeepSeek V3 or R1 had this level of understanding. Neither model understood that it needed to split the job in between instructions to Keyboard Maestro and Chrome. It likewise had fairly weak understanding of AppleScript, writing custom-made regimens for AppleScript that are native to the language.

Weirdly, the R1 model failed as well because it made a bunch of incorrect assumptions. It presumed that a front window always exists, which is absolutely not the case. It also made the presumption that the presently front running program would always be Chrome, instead of clearly to see if Chrome was running.

This leaves DeepSeek V3 with three correct tests and one stop working and DeepSeek R1 with 2 appropriate tests and two stops working.

Final ideas

I discovered that DeepSeek’s persistence on utilizing a public cloud e-mail address like gmail.com (rather than my regular 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 utilize ChatGPT to write code: What it succeeds and what it doesn’t

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

DeepSeek’s online services have just recently dealt with large-scale harmful attacks. To make sure continued service, registration is momentarily restricted to +86 phone numbers. Existing users can visit as typical. Thanks for your understanding and assistance.

Then, I got in and was able to run the tests.

DeepSeek appears to be excessively loquacious in terms of the code it creates. The AppleScript code in Test 4 was both wrong and excessively long. The routine expression code in Test 2 was proper in V3, however it might have been written in a way that made it far more maintainable. It stopped working in R1.

Also: If ChatGPT produces AI-generated code for your app, who does it truly belong to?

I’m absolutely pleased that DeepSeek V3 beat out Gemini, Copilot, and Meta. But it seems at the old GPT-3.5 level, which indicates there’s absolutely room for improvement. I was dissatisfied with the results for the R1 design. Given the option, I ‘d still choose ChatGPT as my programs code assistant.

That stated, for a brand-new tool working on much lower infrastructure than the other tools, this could be an AI to watch.

What do you believe? Have you tried DeepSeek? Are you using any AIs for programming support? Let us understand in the comments below.

You can follow my daily project updates on social media. Make sure to sign up for my weekly upgrade 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.