Multimodal Hallucination - VH Human Resistance: leaderboard
The "VH Human Resistance" subtask of Multimodal Hallucination. A task measuring hallucination in multimodal models — how often a vision-language model asserts objects, attributes or facts not supported by the image.
Metric: Resistance (100 - Human). Source: huggingface.co. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama-VID | 74.47 | |
| 2 | Video-Llama | 68.86 | |
| 3 | MPLUG-Owl2 | 65.89 | |
| 4 | LLaVA-v1.5 | 61.76 | |
| 5 | Video-LLaVA | 61.28 | |
| 6 | Chat-Univi | 57.66 | |
| 7 | FAVOR | 55.5 | |
| 8 | Valley | 46.09 | |
| 9 | InstructBLIP | 42.75 |
Interactive version: theaggregate.ai/benchmark?slug=multimodal-hallucination-vh-human-resistance · How It Works · Data refreshed daily, snapshot 2026-10-20.