AGC-Bench - outline_to_story — leaderboard
Metric: Dataset z-score. Source: huggingface.co. 82 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 1.81 |
| 2 | GLM-5 | 1.74 |
| 3 | GLM-5.1 | 1.58 |
| 4 | GLM-5-Turbo | 1.45 |
| 5 | Gemma 4 26B A4B (IT) | 1.34 |
| 6 | GPT-5.5 | 1.31 |
| 7 | GLM-4.7 | 1.25 |
| 8 | DeepSeek V3.1 Terminus | 1.14 |
| 9 | Llama 3.3 70B Instruct | 1.11 |
| 10 | Llama 4 Scout | 1.11 |
| 11 | GPT-5.4 | 1.06 |
| 12 | Llama 3.1 70B Instruct | 1.05 |
| 13 | DeepSeek V3.2 Exp | 1.04 |
| 14 | DeepSeek V3.2 | 1.03 |
| 15 | jamba-large-1.7 | 1.02 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-outline-to-story · How the rankings work · Data refreshed daily, snapshot 2026-07-22.