GranFact Benchmark

What is GranFact?

A granularity-aware evaluation of whether multimodal models produce visually correct descriptions at reliably specific category levels.

Released

2026-06-28

Evaluates

General AI, Multimodal

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.29573

GranFact paper and code

• Paper https://arxiv.org/abs/2606.29573
• Code https://github.com/WeiWu2025/GranFact

Which sources cite GranFact?

• GranFact

Related General AI, Multimodal benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A-Bench
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ActBench