StoryAlign: leaderboard
Story generation aims to automatically produce coherent, structured, and engaging narratives. Although large language models (LLMs) have significantly advanced text generation, stories generated by LLMs still diverge from human-authored works regarding complex narrative structure and human-aligned preferences. A key reason is the absence of effective modeling of human story preferences, which are
Metric: Average (self-reported). Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 66.3 | #343 |
| 2 | Grok 3 | 62.4 | #304 |
| 3 | Gemini 2.5 Pro | 56.8 | #152 |
| 4 | Qwen 3 8B | 53.5 | #674 |
| 5 | ArmoRM-Llama3-8B-v0.1 | 49.7 | #1394 |
| 6 | Llama 3.1 8B Instruct | 24.3 | #1035 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=storyalign · How It Works · Data refreshed daily, snapshot 2026-10-20.