https://laugh.so/research/judge-leaderboard/
What if LLMs were good banter?Well we tested which LLMs have the best sense of humor.More specifically, we tested 16 top LLMs align most with human sense of humor. We ran >100k judgements and got >1.6k human ratings to see where do we agree across clean and dark jokes.The main findings:- Gemini 3.7 Flash has the best taste at 64% although it's really close at the top- However, we've...
What if you could measure humor?Well we've trained a model on our own dataset of ~50k human ratings to detect what jokes people find funniest. We know it's part objective, part subjective component. Subjective is out of our depth for now hahaThe main results: Fable 5 is funniest - beating the average model 67% of the time, with GPT 4o last at 17%.Other findings: - The models never refused to...
https://www.loom.com/share/a7e164ae1c3e41618e9a8278307735af?sid=1e6191be-762b-40c1-af57-9a319c0259fb
If you get stuck when trying a SaaS product and can't find the answer to your question pretty much instantly you're going to try something else.Our magic search widget will give you instant visual answers to your questions by generating a product walkthrough for you on the fly.Would love to hear your thoughts.