Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

Multimodal Hallucination - VH SelfCheckGPT Resistance — leaderboard

Metric: Resistance (100 - SelfCheckGPT). Source: huggingface.co. 9 models tracked.

Top models

#ModelScore
1InstructBLIP88.32
2LLaVA-v1.587.43
3FAVOR86.22
4Llama-VID85.14
5MPLUG-Owl283.93
6Chat-Univi83.2
7Video-LLaVA80.03
8Video-Llama77.01
9Valley74.31

Interactive version: theaggregate.ai/benchmark?slug=multimodal-hallucination-vh-selfcheckgpt-resistance · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.