AGC-Bench - story_quality — leaderboard

Metric: Dataset z-score. Source: huggingface.co. 82 models tracked.

Top models

#ModelScore
1Mistral Medium 3.11.38
2Hermes 4 405B1.31
3Hermes 4 70B1.24
4GPT-4.1 Mini1.22
5Gemma 3 12B (IT)1.2
6GPT-4o Mini1.14
7Olmo 3.1 32B Instruct1.11
8NVIDIA Nemotron Nano 9B V21.11
9Llama 3.3 70B Instruct1.03
10GPT-4o0.98
11Mixtral 8x22B Instruct0.98
12Gemma 2 27B (IT)0.96
13GPT-5.4 Nano0.94
14DeepSeek V3.20.89
15DeepSeek V3.2 Exp0.83

Interactive version: theaggregate.ai/benchmark?slug=agc-bench-story-quality · How the rankings work · Data refreshed daily, snapshot 2026-07-22.