Multimodal Hallucination - VH CrossCheck-implicit Resistance: leaderboard
The "VH CrossCheck-implicit 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 - CrossCheck-implicit). Source: huggingface.co. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama-VID | 67.59 | |
| 2 | Video-Llama | 66.48 | |
| 3 | MPLUG-Owl2 | 65.57 | |
| 4 | LLaVA-v1.5 | 65.19 | |
| 5 | Video-LLaVA | 63.83 | |
| 6 | Chat-Univi | 61.97 | |
| 7 | Valley | 61.28 | |
| 8 | FAVOR | 51.29 | |
| 9 | InstructBLIP | 50.01 |
Interactive version: theaggregate.ai/benchmark?slug=multimodal-hallucination-vh-crosscheck-implicit-resistance · How It Works · Data refreshed daily, snapshot 2026-10-20.