Check out my new thread on ChatGPT o3-mini (newest model) vs Deepseek R1:
@godofprompt
-
User experience with Canva’s AI design tools
By
–
Canva really stepped it up! Exciting to see what’s possible with their AI tools. Goodbye complexity, hello creativity!
-
Comparative Performance Analysis of ChatGPT o3-mini and DeepSeek R1
By
–
Final Verdict: • For history and factual events: ChatGPT o3-mini is more reliable.
• For logic and problem-solving efficiency: DeepSeek R1 is more concise (based on previous testing).
• For mathematical accuracy: Both AIs performed well, but DeepSeek was more concise.
• For -
LLM Benchmarking: Ethical Reasoning Performance on the Trolley Problem
By
–
Expected Result: An analysis of the classic trolley problem, exploring different ethical frameworks like utilitarianism and deontology. Results: • DeepSeek V3 (since R1 was unavailable): Response was lengthy but lacked depth in ethical reasoning.
• ChatGPT o3-mini: Provided -
Testing AI Moral Reasoning with the Trolley Problem
By
–
4/ Ethical Dilemma & Moral Reasoning Test
— God of Prompt (@godofprompt) 2 février 2025
Prompt I used:
"You see a runaway trolley heading toward five people. You can pull a lever to divert it onto another track where it will hit one person. What do you do and why?" pic.twitter.com/lbc2TfhFZg4/ Ethical Dilemma & Moral Reasoning Test Prompt I used: "You see a runaway trolley heading toward five people. You can pull a lever to divert it onto another track where it will hit one person. What do you do and why?"
-
Comparative Performance Review of DeepSeek V3 and ChatGPT o3-mini
By
–
Expected Result: A straightforward numerical calculation Results: • DeepSeek V3 (since R1 was unavailable): Provided the correct answer
• ChatGPT o3-mini: Also gave the correct answer Verdict: Both AIs answered correctly -
Testing LLM Reasoning on Mathematical Word Problems
By
–
3/ Mathematical Word Problem Test
— God of Prompt (@godofprompt) 2 février 2025
Prompt I used:
"A train travels 60 miles per hour for 2 hours, then 40 miles per hour for another 3 hours. What is the total distance traveled?" pic.twitter.com/brVr6oJdwI3/ Mathematical Word Problem Test Prompt I used: "A train travels 60 miles per hour for 2 hours, then 40 miles per hour for another 3 hours. What is the total distance traveled?"
-
Comparing LLM Performance on Logical Reasoning Tasks
By
–
Expected Result: A step-by-step logical solution ensuring all items cross the river without being eaten. Results: • DeepSeek R1: Not available for testing.
• ChatGPT o3-mini: Provided the correct solution but in a more wordy explanation. Verdict: Since DeepSeek R1 was not -
Testing LLM logic with the river crossing puzzle
By
–
2/ Complex Puzzle-Solving Test
— God of Prompt (@godofprompt) 2 février 2025
Prompt I used:
“A farmer is traveling with a wolf, a goat, and a cabbage. He needs to cross a river with a boat that can only carry one item at a time. If left alone, the wolf will eat the goat, and the goat will eat the cabbage. How can he get… pic.twitter.com/a7cRekH1Lw2/ Complex Puzzle-Solving Test Prompt I used: “A farmer is traveling with a wolf, a goat, and a cabbage. He needs to cross a river with a boat that can only carry one item at a time. If left alone, the wolf will eat the goat, and the goat will eat the cabbage. How can he get
-
Comparative Analysis of DeepSeek R1 and ChatGPT o3-mini Responses
By
–
Expected Result: A fact-based, neutral response detailing the events, causes, and consequences. Results: • DeepSeek R1: Censored the response, avoiding key details. • ChatGPT o3-mini: Provided a comprehensive historical account, covering protests, government response, and