HotComment - Stylistic Resonance (Text): leaderboard

HotComment (2026) asks models to write comments on news articles from NetEase News and Tencent News that would become popular. The stylistic resonance score averages Qwen3-14B and GPT-4o ratings of linguistic expression, creativity, emotional resonance and social or cultural influence, higher is better.

Metric: Stylistic Resonance Score: the mean of four stylistic dimensions (linguistic expression, creative imagination, emotional resonance, social and cultural influence), each the average of Qwen3-14B and GPT-4o ratings, for comments generated zero-shot for held-out HotComment test items (a time- and topic-stratified 10% split) on news articles from NetEase News and Tencent News; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-4o57.09#751
2Qwen2.5-14B-Instruct [8bit]51.78
3Mistral-7B-Instruct [8bit]49.58
4Llama 3.1 8B Instruct [8bit]47.66
5Qwen2.5-7B-Instruct [8bit]45.17
6Baichuan2-7B-Chat [8bit]39.58
7Qwen2.5-0.5B-Instruct [8bit]31.34

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=hotcomment-stylistic-resonance-text · How It Works · Data refreshed daily, snapshot 2026-11-21.