CRAG-MM-Diagnostics Benchmark

What is CRAG-MM-Diagnostics?

CRAG-MM-Diagnostics is a diagnostic benchmark for knowledge-intensive visual question answering (KI-VQA) with stage-wise annotations to isolate visual…

Released

2026-07-23

Evaluates

Factuality, General AI, Information retrieval, Reasoning, Vision & 3D

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.21155

CRAG-MM-Diagnostics paper

• Paper https://arxiv.org/abs/2607.21155

Which sources cite CRAG-MM-Diagnostics?

• CRAG-MM-Diagnostics

Related Factuality, General AI, Information retrieval, Reasoning, Vision & 3D benchmarks

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