ViMU - Structured Subtext Understanding: leaderboard
Metric: Structured subtext understanding (%): the mean of the rhetoric mechanism and social value signal identification scores on ViMU, short online videos whose meaning lies in subtext (irony, mockery, criticism), uniformly sampled frames, zero-shot through official implementations or APIs; questions and references written by GPT-5.4 and reviewed by human experts; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.1 Fast | 31.82 |
| 2 | O4 Mini | 31.36 |
| 3 | Gemini 3 Flash (Preview) | 30.94 |
| 4 | Qwen 3.5 27B | 30.29 |
| 5 | Qwen 3 VL 32B Instruct | 21.41 |
| 6 | Ministral 8B | 21.16 |
| 7 | Gemma 3 27B (IT) | 20.21 |
| 8 | MiMo-V2-Omni | 19.78 |
| 9 | GPT-5.2 | 18.85 |
| 10 | Seed 2.0 Lite | 17.74 |
| 11 | Ministral 3 14B | 16.93 |
| 12 | Gemma 3 4B (IT) | 14.13 |
| 13 | GLM-4.5V | 9.06 |
| 14 | GPT-5.4 Mini | 7.97 |
| 15 | GPT-4.1 Nano | 5.67 |
Interactive version: theaggregate.ai/benchmark?slug=vimu-structured-subtext-understanding · How It Works · Data refreshed daily, snapshot 2026-10-07.