jauws

Definitely on the to-do list! Right now, there's smth called fork (inspired by Github fork), where it lets you remix the story with a given input. It might be cool for you to mess around with.

Thanks Josh! I tried GEPA previously back when it was still 1-shot generation. It actually ended up working really well for some models and horrible for others, so I decided to scrap for a more generic prompt instead to make the benchmark a bit more rigourous.

If you look at similar live benchmarks like LMArena or Design Arena, there's an extremely large number of unique annotators, with a low number of annotations per person - which is normal. However, since this platform is designed to generate fiction catered to individual interests, my hypothesis is that it'll be an added boost of novelty that will help aggregate enough usable data over time.

I hope it's clear that the stories aren't being generated one-shot. I'm sure there are flaws that I haven't perfectly accounted for in the agent-loop, but because we randomize the models for each of the brainstorming -> writing -> memory parts, bad intermediate outputs will affect the final output as well. That's why unless we have above average models across all 3 stages, it might be worse than what you're used to. It's a trade-off to get more granular results. Hope you can give it a chance.

Realistically, I don't think anyone will be spending hours here instead of reading real fiction anytime soon (I personally wouldn't). There's just so much nuanced complexity when it comes to creative writing as a domain (long-form outputs, creativity, etc.) that coming up with better annotation methods has massive applications in other research, like in scientific discovery. "AI Wattpad" just happens to be a convenient form factor for crowdsourcing from an HCI perspective. I hope you give it a chance.

Happy to engage if you have concrete criticisms.

If you have specific objections, I’m open to hearing them.

Would love to chat! Here's my email: team@narrator.sh

Thanks for the feedback. What would you need to see to change your mind?

Thanks for the feedback - looking at the rest of the comments, I definitely agree it seems to be a common theme. Will do better to fix those issues so there's less noise.

I think there's interesting work to be built on this data beyond just generating and sorting slop. I didn't build this because I enjoy having people read bad fiction. I built it because existing benchmarks for creative writing are genuinely bad and often measure the wrong things. The goal isn't to ask users to read low-quality output for its own sake. It's to collect real reader-side signal for a category where automated evaluation has repeatedly failed.

More broadly, crowdsourced data where human inputs are fundamentally diverse lets us study problems that static benchmarks can't touch. The recent "Artificial Hivemind" paper (Jiang et al., NeurIPS 2025 Best Paper) showed that LLMs exhibit striking mode collapse on open-ended tasks, both within models and across model families, and that current reward models are poorly calibrated to diverse human preferences. Fiction at scale is exactly the kind of data you need to diagnose and measure this. You can see where models converge on the same tropes, whether "creative" behavior actually persists or collapses into the same patterns, and how novelty degrades over time. That signal matters well beyond fiction, including domains like scientific research where convergence versus originality really matters.

There's 151 models there right now (with all the latest Anthropic models), it's all randomized, it's just that there aren't enough annotations for the anthropic models to be elicited right now.

Thanks for letting me know - the UI issues are definitely on me (fixing asap). Feel free to generate a story or two - right now there's not enough annotations to make "top-rated" a valid moniker.

Ah shoot - thanks for letting me know. I'm still a noob on frontend so still learning as I go.

Thanks! Anecdotally, I'd tend to say that Claude 3.7 tends to improve the most, but it seems like (via the leaderboard), some people really prefer Grok-3 lol.

Thanks for the comment! Do you mind linking the site - would love to check it out! That's a very fair point about the technical error aspect. Though with all the confounding variables (author skill differences, model selection based on price/speed, etc.) I'd say it's probably the most mature signal we have right now, but still far from ideal.

Really interested in what you've been working on for the past year! Are you doing custom fine-tuning or more on the prompting/post-processing side? Also I definitely need to check out the Midjourney onboarding, it sounds super interesting for inspo regarding your point about personalization + taste!

This is an amazing suggestion! Will definitely try to figure out a way to incorporate this into the leaderboard without making it a constant each time. I'm currently using OpenRouter's default parameters which is totally a brainfart on my part.

Thanks Johnny! I totally agree with you, really appreciate you for checking out my project!