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 sticks out for 3 powerful factors:

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

2. It’s open source.

3. It uses greatly less infrastructure 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 issues over TikTok and possible Chinese federal government participation because 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 post Why China’s DeepSeek might break our AI bubble.

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

Choose V3 for tasks needing depth and precision (e.g., solving advanced mathematics problems, creating complex code).

Choose R1 for latency-sensitive, high-volume applications (e.g., customer support automation, basic 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 utilizing R1.

The brief response is this: impressive, 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 expertise, way back in the day. My other half needed a plugin for WordPress that would help her run a participation gadget for her online group.

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

Her requirements were relatively simple. It needed to take in a list of names, one name per line. It then had to sort 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 offer the AI the challenge on an impulse. To my big surprise, it worked.

Since then, it’s been my very first test for AIs when examining their programs abilities. It requires the AI to understand how to set up code for the WordPress framework and follow prompts plainly adequate to produce both the interface and program logic.

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

DeepSeek V3 produced both the user interface and program reasoning precisely as defined. When It Comes To DeepSeek R1, well that’s a fascinating case. The “thinking” aspect of R1 triggered the AI to spit out 4502 words of analysis before sharing the code.

The UI looked different, with much broader 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 4 tests.

Test 2: Rewriting a string function

A user grumbled that he was not able to enter dollars and cents into a contribution entry field. As written, my code only permitted dollars. So, the test involves providing the AI the routine that I wrote and asking it to rewrite it to permit both dollars and cents

Also: My preferred ChatGPT function just got method more effective

Usually, this leads to the AI producing some regular expression recognition code. DeepSeek did create code that works, although there is room for enhancement. The code that DeepSeek V2 wrote was needlessly long and repetitive while the reasoning before generating the code in R1 was also very long.

My greatest concern is that both models of the DeepSeek validation guarantees validation approximately 2 decimal locations, however if a very large number is gone into (like 0.30000000000000004), the usage of parseFloat does not have specific rounding knowledge. The R1 design also utilized JavaScript’s Number conversion without looking for edge case inputs. If bad information comes back from an earlier part of the routine expression or a non-string makes it into that conversion, the code would crash.

It’s odd, since R1 did provide a very good list of tests to confirm against:

So here, we have a split choice. I’m offering the point to DeepSeek V3 since neither of these issues its code produced would trigger the program to break when run by a user and would create the expected outcomes. On the other hand, I need to offer a fail to R1 since if something that’s not a string somehow enters the Number function, a crash will ensue.

Which offers DeepSeek V3 2 wins out of 4, however DeepSeek R1 just one win out of four so far.

Test 3: Finding an annoying bug

This is a test created when I had a really bothersome bug that I had problem finding. Once again, I decided to see if ChatGPT could handle it, which it did.

The difficulty is that the response isn’t obvious. Actually, the obstacle is that there is an apparent answer, based upon the mistake message. But the apparent response is the incorrect answer. This not only captured me, however it frequently captures 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 particular API calls within WordPress work, having the ability 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 nearly similar responses, bringing us to three out of four wins for V3 and two out of 4 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 tough test since it requires the AI to understand the interplay in between 3 environments: AppleScript, the Chrome object model, and a Mac scripting tool called Keyboard Maestro.

I would have called this an unreasonable test due to the fact that Keyboard Maestro is not a traditional programming tool. But ChatGPT managed the test quickly, comprehending exactly what part of the issue is dealt with 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 understood that it required to split the job between guidelines to Keyboard Maestro and Chrome. It likewise had fairly weak knowledge of AppleScript, writing custom-made regimens for AppleScript that are belonging to the language.

Weirdly, the R1 model failed too because it made a lot of incorrect presumptions. It presumed that a front window always exists, which is certainly not the case. It also made the assumption that the presently front running program would always be Chrome, instead of explicitly checking to see if Chrome was running.

This leaves DeepSeek V3 with three proper tests and one fail and DeepSeek R1 with 2 proper tests and 2 fails.

Final ideas

I found that DeepSeek’s persistence on using a public cloud e-mail address like gmail.com (instead of my typical e-mail address with my corporate domain) was annoying. It likewise 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 succeeds and what it doesn’t

I wasn’t sure I ‘d be able to write this post since, for most of the day, I got this error when attempting to sign up:

DeepSeek’s online services have actually just recently dealt with massive destructive attacks. To make sure continued service, registration is temporarily restricted to +86 phone numbers. Existing users can visit as typical. Thanks for your understanding and support.

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

DeepSeek appears to be extremely chatty in regards to the code it generates. The AppleScript code in Test 4 was both incorrect and exceedingly long. The routine expression code in Test 2 was proper in V3, however it could have been composed in a way that made it far more maintainable. It failed in R1.

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

I’m definitely impressed that DeepSeek V3 beat out Gemini, Copilot, and Meta. But it seems at the old GPT-3.5 level, which implies there’s definitely space for enhancement. I was disappointed with the results for the R1 model. Given the option, I ‘d still choose ChatGPT as my shows code assistant.

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

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

You can follow my updates on social media. Make certain to subscribe to 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.