# Facts-VLM

> A grounded multimodal factuality benchmark for evidence-linked answer correctness.

Canonical page: https://benchlm.ai/benchmarks/factsvlm

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: September 27, 2026

## About Facts-VLM

- Year: 2026
- Tasks: Grounded factuality tasks
- Format: Evidence-linked multimodal factuality
- Difficulty: Grounded multimodal factuality
- Paper: [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo)

BenchLM stores Facts-VLM as a display-only benchmark reference when exact provider tables are available.

Facts-VLM is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (0 models)

Benchmark data for this page is coming soon.

## FAQ

### What does Facts-VLM measure?

A grounded multimodal factuality benchmark for evidence-linked answer correctness.

### Which model scores highest on Facts-VLM?

No models have been evaluated on Facts-VLM yet.

### How many models are evaluated on Facts-VLM?

0 AI models have been evaluated on Facts-VLM on BenchLM.

### Does Facts-VLM affect BenchLM's overall score?

Not directly. Facts-VLM is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.