ViMU - Open-Ended Interpretation: leaderboard
ViMU (2026) benchmarks video metaphorical understanding: whether models grasp the implicit, ironic or socially coded meaning of short online videos. This board is a rubric score in percent from an LLM judge for open-ended explanations of the intended meaning, penalizing hallucinated and purely literal answers; higher is better.
Metric: Open-ended interpretation score (%): an LLM judge rubric over core intent, implicit signal and social target, minus hallucination and literal-only penalties, rescaled to percent, hint-free questions 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 March 2027. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 73.15 | #185 |
| 2 | GPT-5.4 Mini | 66.19 | #406 |
| 3 | O4 Mini | 65.27 | #368 |
| 4 | Qwen 3 VL 32B Instruct | 64.09 | #606 |
| 5 | MiMo-V2-Omni | 64.07 | #465 |
| 6 | Qwen 3.5 27B | 62.8 | #375 |
| 7 | Gemini 3 Flash (Preview) | 62.54 | #152 |
| 8 | GLM-4.5V | 62.52 | #754 |
| 9 | Seed 2.0 Lite | 60.84 | #300 |
| 10 | Grok 4.1 Fast | 57.62 | #427 |
| 11 | Gemma 3 27B (IT) | 55.9 | #1324 |
| 12 | Ministral 3 14B | 52.19 | #1870 |
| 13 | Claude 3 Haiku | 50.41 | #2663 |
| 14 | GPT-4.1 Nano | 50.12 | #2056 |
| 15 | Ministral 8B | 48.25 | #4857 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=vimu-open-ended-interpretation · How It Works · Data refreshed daily, snapshot 2026-11-21.