GTP Blind Voting: GPT-5 vs. 4o

#1

Post by findhorn » Fri, Aug 08, 2025, 11:11 PM UTC

https://x.com/flowersslop/status/1953908930897158599

GTP Blind Voting: GPT-5 vs. 4o
gptblindvoting.vercel.app

Re: GTP Blind Voting: GPT-5 vs. 4o

#2

Post by zipping1549 » Sat, Aug 09, 2025, 4:55 AM UTC

I feel like the questions are way too simple. 3B models may perform similar with this sort of questions.

Re: GTP Blind Voting: GPT-5 vs. 4o

#3

Post by JoshuaDavid » Sat, Aug 09, 2025, 5:25 AM UTC

It is striking how similar these answers are to each other, hitting the same points beat for beat in a slightly different tone.

Re: GTP Blind Voting: GPT-5 vs. 4o

#4

Post by ggoo » Sat, Aug 09, 2025, 5:00 PM UTC

19/20 for gpt5. All the answers were very similar though I mostly just felt like the tone and delivery was better.

Re: GTP Blind Voting: GPT-5 vs. 4o

#5

Post by imafish » Sun, Aug 10, 2025, 11:09 AM UTC

ggoo wrote: post #4

19/20 for gpt5. All the answers were very similar though I mostly just felt like the tone and delivery was better.

Interesting. 6/10 for gpt5 here.

Re: GTP Blind Voting: GPT-5 vs. 4o

#6

Post by FergusArgyll » Sun, Aug 10, 2025, 11:09 AM UTC

It's the same model

Re: GTP Blind Voting: GPT-5 vs. 4o

#7

Post by ismailmaj » Sun, Aug 10, 2025, 11:17 AM UTC

There should be a “both” option, I often found both answers acceptable but sometimes I strictly preferred one and those get sadly watered down.

Re: GTP Blind Voting: GPT-5 vs. 4o

#8

Post by Workaccount2 » Sun, Aug 10, 2025, 11:17 AM UTC

ggoo wrote: post #4

19/20 for gpt5. All the answers were very similar though I mostly just felt like the tone and delivery was better.

8/10 gpt-5

Re: GTP Blind Voting: GPT-5 vs. 4o

#9

Post by croes » Sun, Aug 10, 2025, 11:18 AM UTC

This is a voting about the tone and note the quality of the answers.

Re: GTP Blind Voting: GPT-5 vs. 4o

#10

Post by mrtksn » Sun, Aug 10, 2025, 11:22 AM UTC

My understanding was that with GPT-5 you don't actually get the high quality stuff unless the system decides that you need it. So, for simple questions you end up getting the subpar response. A bit like not getting hot water until you increase the flow enough to trigger the boiler to start the heating.

Lately I enjoy Grok the most for simple questions, even if it isn't necessarily about a recent event. Then I like OpenAI, Mistral, Deepseek equally and for some reason never felt good about Gemini. Tried switching to Gemini Pro the last two months but I found myslef going back to ChatGPT's free mode and Grok's free mode. Cancelled yesterday and now happily back to ChatGPT Plus.

I got %80 GPT-5 preference anyway.