Thanks for dropping by The Agora Lab!

​

Who am I?

 

Here's my background in case you're curious why someone would start a blog like this when there are already so many AI benchmarks out there!

 

I have a PhD in Psychology. Though my expertise isn't directly in LLMs, I use ChatGPT, Claude, and Gemini almost every single day for different kinds of work. People generally assume which model is good at what. I did too, but for important questions, I'd copy and paste the same prompt into all three. To my surprise, they sometimes come up with very different answers, and the model that turns out to be best isn't always the one I expected.

 

Why The Agora lab?

​

There are a lot of AI benchmarks out there, but they typically measure things like science questions or passing the bar — not the kinds of tasks we actually use AI for.

 

That's why the researcher in me wants to start testing them properly on different tasks that an average person actually cares about — things like editing emails or writing a CV, researching options, creative tasks like writing your Instagram Reels script, or even something more personal like asking for relationship advice.

 

I've spent years designing experiments, evaluating written work, and grading more papers than I can count. That's exactly what I bring to AI comparisons. I design experiments testing ChatGPT, Claude, and Gemini using the same prompt, under the same conditions, and scoring them on specific criteria. No sponsorships, no affiliations — just honest evaluations from someone trained to assess the quality of written and analytical work.

 

That's what The Agora Lab is. Real, side-by-side AI comparisons for the things you actually care about — writing, research, creative work, everyday productivity. Plus practical tips on how to prompt each AI to get better results.

 

This is also why I built Agora. Through running these experiments, I kept finding that the best answer rarely comes from just one AI. So I built something that lets you ask all three AIs at once, then carefully analyzes their responses and gives you one clear answer that's better than any single AI. You can even have them debate each other to go deeper.

 

If you're curious, you can try it at askagora.ai.

 

But you don't need Agora to benefit from this blog. Every comparison here is free and open — use it to figure out which AI is worth your time.

 

Happy browsing!