DataComp for VLMs (DCVLM) Benchmark

What is DataComp for VLMs (DCVLM)?

A controlled benchmark for comparing vision-language training-data curation strategies across specified model scales and token budgets.

Released

2026-06-26

Evaluates

General AI, Multimodal

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.28551

DataComp for VLMs (DCVLM) paper

• Paper https://arxiv.org/abs/2606.28551
• Website https://www.datacomp.ai/dcvlm/

Which sources cite DataComp for VLMs (DCVLM)?

• DataComp for VLMs (DCVLM)

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