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 previous weekend. It stands out for three effective reasons:

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

2. It’s open source.

3. It utilizes significantly less facilities than the big AI tools we’ve been looking at.

Also: Apple scientists expose the secret sauce behind DeepSeek AI

Given the US government’s concerns over TikTok and possible Chinese government participation in that code, a brand-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 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 have actually thrown at 10 other big language designs. According to DeepSeek itself:

Choose V3 for tasks requiring depth and precision (e.g., solving innovative mathematics problems, creating complicated code).

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

You can pick 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 short answer is this: remarkable, but 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 expertise, way back in the day. My spouse needed a plugin for WordPress that would help her run an involvement device for her online group.

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

Her requirements 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, different them so they weren’t noted side-by-side.

I didn’t actually have time to code it for her, so I chose to offer 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 evaluating their programs abilities. It requires the AI to understand how to set up code for the WordPress framework and follow triggers plainly enough to develop both the user interface and program logic.

Only about half of the AIs I’ve checked can fully pass this test. Now, however, we can add another to the winner’s circle.

DeepSeek V3 developed both the user interface and program reasoning precisely as defined. As for DeepSeek R1, well that’s a fascinating case. The “thinking” element of R1 caused the AI to spit out 4502 words of analysis before sharing the code.

The UI looked various, with much broader 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 complained that he was unable to enter dollars and cents into a contribution entry field. As written, my code just enabled dollars. So, the test includes offering the AI the regular that I wrote and asking it to rewrite it to permit both dollars and cents

Also: My favorite ChatGPT function simply got method more powerful

Usually, this leads to the AI producing some routine expression validation code. DeepSeek did create code that works, although there is space for improvement. The code that DeepSeek V2 composed was needlessly long and repetitious while the reasoning before the code in R1 was also extremely long.

My greatest concern is that both designs of the DeepSeek validation makes sure recognition up to 2 decimal locations, however if an extremely big number is gotten in (like 0.30000000000000004), the usage of parseFloat doesn’t have explicit rounding understanding. The R1 design also used JavaScript’s Number conversion without checking for edge case inputs. If bad data 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 provide an extremely great list of tests to validate versus:

So here, we have a split choice. I’m providing the indicate DeepSeek V3 because neither of these concerns its code produced would trigger the program to break when run by a user and would create the anticipated outcomes. On the other hand, I need to offer a fail to R1 because if something that’s not a string somehow enters into the Number function, a crash will take place.

Which gives DeepSeek V3 2 triumphes of 4, however DeepSeek R1 only one win out of 4 up until now.

Test 3: Finding an irritating bug

This is a test created when I had a really irritating bug that I had difficulty finding. Once once again, I decided to see if ChatGPT might handle it, which it did.

The difficulty is that the answer isn’t apparent. Actually, the obstacle is that there is an apparent answer, based upon the error message. But the obvious answer is the incorrect response. This not only caught me, but it frequently catches a few of the AIs.

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

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

Both DeepSeek V3 and R1 passed this one with nearly similar answers, bringing us to 3 out of four wins for V3 and two out of four wins for R1. That already puts DeepSeek ahead of Gemini, Copilot, Claude, and Meta.

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

Test 4: Writing a script

And another one bites the dust. This is a difficult test due to the fact that it needs the AI to comprehend the interaction in between 3 environments: AppleScript, the Chrome item model, and a Mac scripting tool called Keyboard Maestro.

I would have called this an unreasonable test because Keyboard Maestro is not a traditional programming tool. But ChatGPT handled the test quickly, comprehending exactly what part of the issue is handled 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 understanding. Neither model understood that it required to divide the task between guidelines to Keyboard Maestro and Chrome. It likewise had fairly weak understanding of AppleScript, writing custom-made routines for AppleScript that are native to the language.

Weirdly, the R1 design stopped working too since it made a lot of incorrect assumptions. It presumed that a front window constantly exists, which is absolutely not the case. It also made the assumption that the presently front running program would always be Chrome, instead of clearly checking to see if Chrome was running.

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

Final ideas

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 business domain) was bothersome. It likewise had a variety of responsiveness fails that made doing these tests take longer than I would have liked.

Also: How to utilize ChatGPT to compose code: What it succeeds and what it doesn’t

I wasn’t sure I ‘d have the ability to compose this short article since, for most of the day, I got this mistake when trying to sign up:

DeepSeek’s online services have actually just recently faced large-scale destructive attacks. To ensure ongoing service, registration is briefly limited to +86 telephone number. Existing users can log in as typical. Thanks for your understanding and assistance.

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

DeepSeek appears to be overly chatty in regards to the code it produces. The AppleScript code in Test 4 was both incorrect and exceedingly long. The regular expression code in Test 2 was proper in V3, but it could have been written in a method that made it a lot more maintainable. It stopped working in R1.

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

I’m absolutely amazed that DeepSeek V3 vanquished Gemini, Copilot, and Meta. But it appears to be at the old GPT-3.5 level, which means there’s absolutely space for enhancement. I was dissatisfied with the outcomes for the R1 model. Given the option, I ‘d still select ChatGPT as my programming code assistant.

That said, for a new tool operating on much lower infrastructure than the other tools, this could be an AI to enjoy.

What do you believe? Have you attempted DeepSeek? Are you utilizing any AIs for programming assistance? Let us know in the remarks listed below.

You can follow my day-to-day task updates on social media. Be sure 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.