DiCoBench

What is DiCoBench?

DiCoBench evaluates multimodal LLMs on multi-image fine-grained perception using high-resolution (up to 2K) image pairs. It includes 765 multiple-choice…

Released

2026-06-25

Evaluates

General AI, Vision & 3D, cs.CV

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.26602

DiCoBench paper and code

• Paper https://arxiv.org/abs/2606.26602
• Code https://github.com/PKU-ICST-MIPL/DICO_Bench_ECCV2026

Which sources cite DiCoBench?

• DiCoBench

Related General AI, Vision & 3D, cs.CV benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench