ViMU - Structured Subtext Understanding: leaderboard
ViMU (2026) benchmarks video metaphorical understanding: whether models grasp the implicit, ironic or socially coded meaning of short online videos. This board is the mean in percent of the rhetoric mechanism and social value signal identification scores; higher is better.
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. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4.1 Fast | 31.82 | #427 |
| 2 | O4 Mini | 31.36 | #368 |
| 3 | Gemini 3 Flash (Preview) | 30.94 | #152 |
| 4 | Qwen 3.5 27B | 30.29 | #375 |
| 5 | Qwen 3 VL 32B Instruct | 21.41 | #606 |
| 6 | Ministral 8B | 21.16 | #4857 |
| 7 | Gemma 3 27B (IT) | 20.21 | #1324 |
| 8 | MiMo-V2-Omni | 19.78 | #465 |
| 9 | GPT-5.2 | 18.85 | #185 |
| 10 | Seed 2.0 Lite | 17.74 | #300 |
| 11 | Ministral 3 14B | 16.93 | #1870 |
| 12 | Gemma 3 4B (IT) | 14.13 | #4139 |
| 13 | GLM-4.5V | 9.06 | #754 |
| 14 | GPT-5.4 Mini | 7.97 | #406 |
| 15 | GPT-4.1 Nano | 5.67 | #2056 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=vimu-structured-subtext-understanding · How It Works · Data refreshed daily, snapshot 2026-11-21.