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

DeepSeek exploded into the world’s consciousness this previous weekend. It stands apart for three effective factors:

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

2. It’s open source.

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

Also: Apple researchers expose the secret sauce behind DeepSeek AI

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

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

Choose V3 for jobs requiring depth and accuracy (e.g., solving advanced mathematics issues, creating complex code).

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

The short response is this: outstanding, however plainly not best. Let’s dig in.

Test 1: Writing a WordPress plugin

This test was actually my first test of ChatGPT’s programming 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 needs were relatively basic. It required to take in a list of names, one name per line. It then needed to sort the names, and if there were duplicate names, different them so they weren’t listed side-by-side.

I didn’t really have time to code it for her, so I decided to offer 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 requires the AI to know how to establish code for the WordPress framework and follow prompts clearly sufficient to produce both the interface and program logic.

Only about half of the AIs I have actually checked can totally pass this test. Now, however, we can add one more 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 an interesting case. The “reasoning” aspect of R1 caused 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 logic worked, so R1 also passes this test.

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

Test 2: Rewriting a string function

A user grumbled that he was unable to enter dollars and cents into a donation entry field. As written, my code just enabled 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 favorite ChatGPT feature just got method more powerful

Usually, this results in the AI producing some regular expression validation code. DeepSeek did create code that works, although there is space for enhancement. The code that DeepSeek V2 wrote was unnecessarily long and repetitive while the reasoning before producing the code in R1 was also long.

My biggest concern is that both designs of the DeepSeek validation guarantees recognition up to 2 decimal locations, but if a huge number is gotten in (like 0.30000000000000004), using parseFloat does not have knowledge. The R1 model likewise utilized JavaScript’s Number conversion without looking 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 present a very good list of tests to validate against:

So here, we have a split choice. I’m providing 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 outcomes. On the other hand, I need to offer a fail to R1 because 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, however DeepSeek R1 only one win out of 4 so far.

Test 3: Finding an irritating bug

This is a test developed when I had a very bothersome bug that I had difficulty locating. Once again, I decided to see if ChatGPT could manage it, which it did.

The difficulty is that the response isn’t obvious. Actually, the difficulty is that there is an apparent response, based upon the error message. But the obvious response is the wrong answer. This not just caught me, but it routinely 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 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 similar responses, bringing us to 3 out of 4 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 home run for V3? Let’s discover.

Test 4: Writing a script

And another one bites the dust. This is a challenging test since it requires the AI to understand the interaction in between 3 environments: AppleScript, the Chrome item design, and a Mac scripting tool called Keyboard Maestro.

I would have called this an unfair test because Keyboard Maestro is not a mainstream programs tool. But ChatGPT managed the test quickly, understanding exactly what part of the issue 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 knowledge. Neither model understood that it needed to split the job between instructions to Keyboard Maestro and Chrome. It also had relatively weak knowledge of AppleScript, composing custom-made routines for AppleScript that are native to the language.

Weirdly, the R1 model failed as well since it made a lot of incorrect presumptions. It presumed that a front window always exists, which is definitely not the case. It also made the assumption that the currently front running program would always be Chrome, rather than explicitly examining to see if Chrome was running.

This leaves DeepSeek V3 with 3 proper tests and one stop working and DeepSeek R1 with two right tests and two stops working.

Final thoughts

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

Also: How to use ChatGPT to write code: What it succeeds and what it doesn’t

I wasn’t sure I ‘d have the ability to write this short article due to the fact that, for many of the day, I got this error when attempting to register:

DeepSeek’s online services have actually just recently dealt with large-scale harmful attacks. To make sure continued service, registration is temporarily restricted to +86 phone numbers. 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 seems to be extremely chatty in terms of the code it generates. The AppleScript code in Test 4 was both wrong and exceedingly long. The routine expression code in Test 2 was correct in V3, but it could have been written in a way 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 satisfied that DeepSeek V3 beat out Gemini, Copilot, and Meta. But it seems at the old GPT-3.5 level, which suggests there’s absolutely room for enhancement. I was dissatisfied with the results for the R1 model. Given the option, I ‘d still pick ChatGPT as my programs code assistant.

That stated, for a new tool running on much lower facilities 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 programming support? Let us understand in the comments below.

You can follow my day-to-day project 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.