Comments on: Everyone Is Talking About DeepSeek AI, but Is It Really THAT Good? I Tested It Against GPT-o1 and Claude

By: John Baker

John Baker — Sun, 16 Mar 2025 08:40:59 +0000

In reply to User (P). I personally found that DeepSeek R1 appears to perform much worse than GPT-4o. I think this is sometimes because if you hit a problem where it's doing something wrong it gets even better at it! I should also mention that ChatGPT did to me the same thing where it weirdly deleted the response and prompt after the message on a certain topic. There's potentially the same censorship here it's just on different things though it might have also been a glitch.

By: User (P)

User (P) — Thu, 06 Feb 2025 02:02:03 +0000

It doesn’t look like you were actually using the R1 model for DeepSeek. It may have been more fair to compare GPT-4o to DeepSeek V3 and GPT-o1 to DeepSeek R1.

By: Pelumi

Pelumi — Thu, 06 Feb 2025 00:35:31 +0000

Great article by the way

By: Pelumi

Pelumi — Thu, 06 Feb 2025 00:35:11 +0000

What about the Deepthink(R1) feature ??

By: Martin Dubovic

Martin Dubovic — Fri, 31 Jan 2025 18:12:29 +0000

In reply to Mike Rosoft. Thanks for your kind words Mike and for taking the time to leave a comment. I appreciate it and I'm glad you enjoyed the read.

By: Mike Rosoft

Mike Rosoft — Thu, 30 Jan 2025 21:59:05 +0000

I really enjoyed this article—it gives such a well-rounded and insightful look at the new DeepSeek R1 model! The detailed testing and comparisons with GPT-01 and Claude 3.5 Sonnet make it so easy to understand how DeepSeek stacks up. I especially appreciate the real-world examples and the methodical approach.
It’s a fantastic read for anyone interested in the latest AI advancements. Big thanks to Martin Dubovic for putting together such a thorough and engaging analysis!