Well we've trained a model on our own dataset of ~50k human ratings to detect what jokes people find funniest. \nWe know it's part objective, part subjective component. \nSubjective is out of our depth for now haha
The main results: Fable 5 is funniest - beating the average model 67% of the time, with GPT 4o last at 17%.
Other findings:\n - The models never refused to try, even with dark prompts\n - Thinking longer has a slight benefit\n - Absurdness correlates negatively with joke quality
Some methodology notes:\n - We benchmarked our model against the human majority and it agreed 72% of the time in a blind sample test.\n - We had 51 US adults rate the jokes, each blind to the models, with joke order randomized, and quality checked for attention and speed.\n - To rate some yourself visit https://pair.laugh.so
The full benchmark here:
Am taking requests if there's more research you want to see! Cheers","time":1785973712,"title":"Show HN: Humor Arena – Which frontier model is funniest?","type":"story","url":"https://laugh.so/benchmark/"}