Our new X account is live! Follow @wizwand_team for updates

Home/Benchmarks

3D Captioning on Cap3D Cap

134.1CIDEr

X-InstructBLIP

Updated 4d ago

Evaluation Results

Method	Links
X-InstructBLIP 2024.10		134.1
Ours 2024.10		107.6

SOTA Paper

X-InstructBLIP

X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning

Dataset

Cap3D

Follow for update

@wizwand_team Discord

Related Benchmarks

Visual Question Answering on LLaVA Bench 3D Object Classification on ModelNet (test)Audio Captioning on Clotho Caps (test)Video Captioning on MSVD Cap Audio Captioning on AudioCaps (val)

© 2026 wizwand

Blog Contact Changelog

Privacy Policy Terms of Service FAQs