HotComment - Stylistic Resonance (Video): leaderboard
HotComment (2026) asks models to write comments on Bilibili videos 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 Bilibili videos; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini2.5-Image (HotComment checkpoint unspecified) | 56.63 | |
| 2 | GPT-4o | 55.71 | #754 |
| 3 | Mistral-Small-3.1-24B-Instruct [8bit] | 54.25 | |
| 4 | GPT-4o Mini | 52.56 | #1680 |
| 5 | Qwen3-VL-8B-Instruct [8bit] | 49.81 | |
| 6 | HotComment Llama-3.2-Vision-Instruct (size unspecified) [8bit] | 49.43 | |
| 7 | Qwen3-VL-4B-Instruct [8bit] | 34.38 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=hotcomment-stylistic-resonance-video · How It Works · Data refreshed daily, snapshot 2026-11-22.