HoWToBench - Poem: leaderboard
Metric: Tree-of-Writing score: GPT-4o rates each content trait 1-10 against the human reference and format traits 0, 5 or 10, combined with per-instruction LLM-assigned weights that sum to 1, mean over the poem writing instructions of HoWToBench; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-11-20) | 6.34 |
| 2 | O3 Mini (2025-01-31) | 5.81 |
| 3 | Gemini 2.0 Flash | 5.42 |
| 4 | Claude 3.5 Sonnet (20241022) | 5.41 |
| 5 | Claude 3 Haiku (20240307) | 4.58 |
| 6 | Llama 3.3 70B Instruct | 4.2 |
Interactive version: theaggregate.ai/benchmark?slug=howtobench-poem · How It Works · Data refreshed daily, snapshot 2026-10-07.