Facts-VLM (Facts-VLM)

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

Top Models on Facts-VLM — March 2026

As of March 2026, GLM-5V-Turbo leads the Facts-VLM leaderboard with 58.6% , followed by Kimi K2.5 (57.8%).

2 modelsMultimodal & GroundedCurrentDisplay onlyUpdated April 1, 2026

About Facts-VLM

Year

2026

Tasks

Grounded factuality tasks

Format

Evidence-linked multimodal factuality

Difficulty

Grounded multimodal factuality

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

GLM-5V-Turbo

BenchLM freshness & provenance

Version

Facts-VLM 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Leaderboard (2 models)

#1GLM-5V-Turbo
58.6%
#2Kimi K2.5
57.8%

FAQ

What does Facts-VLM measure?

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

Which model scores highest on Facts-VLM?

GLM-5V-Turbo by Zhipu AI currently leads with a score of 58.6% on Facts-VLM.

How many models are evaluated on Facts-VLM?

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

Compare Top Models on Facts-VLM

Last updated: April 1, 2026 · BenchLM version Facts-VLM 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.