AGC-Bench - story_quality — leaderboard
Metric: Dataset z-score. Source: huggingface.co. 82 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Medium 3.1 | 1.38 |
| 2 | Hermes 4 405B | 1.31 |
| 3 | Hermes 4 70B | 1.24 |
| 4 | GPT-4.1 Mini | 1.22 |
| 5 | Gemma 3 12B (IT) | 1.2 |
| 6 | GPT-4o Mini | 1.14 |
| 7 | Olmo 3.1 32B Instruct | 1.11 |
| 8 | NVIDIA Nemotron Nano 9B V2 | 1.11 |
| 9 | Llama 3.3 70B Instruct | 1.03 |
| 10 | GPT-4o | 0.98 |
| 11 | Mixtral 8x22B Instruct | 0.98 |
| 12 | Gemma 2 27B (IT) | 0.96 |
| 13 | GPT-5.4 Nano | 0.94 |
| 14 | DeepSeek V3.2 | 0.89 |
| 15 | DeepSeek V3.2 Exp | 0.83 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-story-quality · How the rankings work · Data refreshed daily, snapshot 2026-07-22.