OpenCodePapers

visual-grounding-on-refcoco-val

Visual Grounding
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks✓ Link93.4OpenVLThinkerV2 (Ours)2026-04-09
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning✓ Link92.57CoME-VL2026-04-03
Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action✓ Link90.7Unified-IO 2 XXL2023-12-28
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection✓ Link90.56Grounding DINO L (Swin-L, fine-tuned)2023-03-09
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond✓ Link89.36Qwen-VL2023-08-24
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features✓ Link88.45SigLIP 2 (g/16) + decoder2025-02-20
PaliGemma 2: A Family of Versatile VLMs for Transfer✓ Link78.2PaliGemma 2 10B2024-12-04
Artemis: Structured Visual Reasoning for Perception Policy Learning✓ Link71.7Artemis2025-12-01
Check out how to contribute new results. Then edit this file on GitLab or GitHub.