List your company

Referring Expression Comprehension on RefCOCO (testA)

94.33AccuracyUNINEXT
-2.81369622.40630247.626372.846298Jun 11, 2020May 11, 2021Apr 11, 2022Mar 12, 2023Feb 10, 2024Jan 10, 2025Dec 11, 2025

Evaluation results

MethodLinks
UNINEXTModel type=Specialist models2023.1094.33————————————
G-DINO-LModel type=Specialist models2023.1093.19————————————
MiniGPT-v2 (7B)Model type=Generalist models2023.1091.65————————————
MiniGPT-v2 (7B)-chatModel type=Generalist models2023.1091.29————————————
Shikra (13B)Model type=Generalist models2023.1091.11————————————
Shikra (7B)Model type=Generalist models2023.1090.61————————————
VisionLLM-HModel type=Generalist models2023.1086.7————————————
OFA-LModel type=Generalist models2023.1083.87————————————
InternVL2.5-78BParameters=78B2024.120.956————————————
Qwen2-VL-72BType=Generalist2024.090.953————————————
Qwen2-VL-72BParameters=72B2024.120.953————————————
Ferret-v2Type=Generalist2024.090.95————————————
Ferret-v2-13B2025.120.95————————————
Ferret-v2-13BParameters=13B2024.120.95————————————
CogVLMType=Generalist2024.090.948————————————
InternVL2-26BType=Generalist2024.090.948————————————
CogVLM-Grounding-17BParameters=17B2024.120.948————————————
InternVL2-Llama3-76BBackbone=Llama3, Parameters=76B2024.120.948————————————
CogVLM-GroundingType=Generalist2023.110.9475————————————
CogVLM-17BModel Size=17B2024.070.9475————————————
InternVL3.5-8B2025.120.947————————————
VGent2025.120.947————————————
C³VGBackbone=BEIT3-ViT-B, Data Size=28K2025.010.946————————————
InternVL3-8B2025.120.946————————————
InternVL2.5-8BParameters=8B2024.120.945————————————
InternVL3-14B2025.120.944————————————
UNINEXT-HModel type=Specialist SOTAs (Specialist/Finetuned)2023.060.9433————————————
UNINEXT-HModel type=Specialist SOTAs2023.080.9433————————————
UNINEXT-HModel Type=Specialist SOTAs2023.110.9433————————————
UNINEXT-HType=Specialist2023.110.9433————————————
UNINEXT-HType=Specialist2024.030.9433————————————
UNINEXT-HModel type=Specialist Models2023.120.9433————————————
Supervised SOTA2023.110.9433————————————
UNINEXT-HType=Specialist2024.090.943————————————
UNINEXT-H2025.120.943————————————
UNINEXT-HBackbone=Huge2024.120.943————————————
ASMv2-13BParameters=13B2024.020.9424————————————
ONE-PEACEType=Specialist2024.090.942————————————
ONE-PEACE2025.120.942————————————
CoT4DET-7BType=MLLM2025.120.942————————————
ONE-PEACE2024.120.942————————————
ONE-PEACEModel type=Specialist SOTAs (Specialist/Finetuned)2023.060.9418————————————
ONE-PEACEModel type=Specialist SOTAs2023.080.9418————————————
ONE-PEACEType=Specialist2023.110.9418————————————
ONE-PEACEType=Specialist2024.030.9418————————————
InternVL3.5-20B-A4B2025.120.941————————————
CogVLM2023.120.9395————————————
Emu2-Chat2023.120.9388————————————
CoS-7BModel Size=7B, Fine-tuning protocol=LoRA2024.070.9383————————————
Qwen2-VL-7BType=Generalist2024.090.936————————————
Qwen2-VL-7B2025.120.936————————————
Qwen2-VL-7BType=MLLM2025.120.936————————————
Qwen2-VL-7BParameters=7B2024.120.936————————————
Qwen-VLType=Generalist, tuning=SC-Tune, Locator training stage (Lsup)=true2024.030.9343————————————
PerceptionGPT-13BModel Type=Generalist VL SOTAs2023.110.932————————————
G-DINO-LType=Specialist2024.090.932————————————
Grounding-DINO-L2025.120.932————————————
InternVL3-9B2025.120.932————————————
Grounding-DINO-LBackbone=Large2024.120.932————————————
G-DINO-LModel type=Specialist SOTAs (Specialist/Finetuned)2023.060.9319————————————
G-DINO-LModel type=Specialist SOTAs2023.080.9319————————————
G-DINO-LType=Specialist2023.110.9319————————————
G-DINO-LType=Specialist2024.030.9319————————————
G-DINO-LModel type=Specialist Models2023.120.9319————————————
LION-12BEvaluation Setting=Fine-tuning Setting2023.110.9302————————————
LION-12BBackbone=Flan-T5-11B, Data Size=3.6M2025.010.9302————————————
TextHawk22024.120.93————————————
VILLA_LARGEdetected proposals=false, Model Scale=LARGE2020.060.9296————————————
OFA-LPre-training data (Im-Txt)=true, Pre-training data (Im-Txt-Box)=true2022.060.9293————————————
OFA-LVisual Backbone=RN152, Text Encoder=Embedding layer2023.020.9293————————————
OFAzero-shot=false2023.060.9293————————————
PolyFormer-LVisual Backbone=Swin-L, Text Encoder=BERT-base2023.020.9289————————————
SimVGBackbone=BEIT3-ViT-B, Data Size=174K2025.010.928————————————
VILLA_BASEdetected proposals=false, Model Scale=BASE2020.060.9279————————————
EEVGBackbone=ViT-B, Data Size=174K2025.010.9273————————————
UNITER_LARGEdetected proposals=false, Model Scale=LARGE2020.060.9265————————————
FIBER-BPre-training data (Im-Txt)=true, Pre-training data (Im-Txt-Box)=true2022.060.9259————————————
FIBERzero-shot=false2023.060.9259————————————
SimVG-TBVisual Encoder=ViT-L/32, Time (ms)=1012024.090.9253————————————
PerceptionGPT-7BModel Type=Generalist VL SOTAs2023.110.9251————————————
Qwen2.5-VL-7B2025.120.925————————————
Qwen2.5-VL-7BType=MLLM2025.120.925————————————
MM1.52024.120.925————————————
Ferret-13BEvaluation Setting=Fine-tuning Setting2023.110.9241————————————
Ferret-13BType=Generalist2023.110.9241————————————
Ferret-13BModel Size=13B2024.070.9241————————————
Ferret-13BParameters=13B2024.020.9241————————————
SimVG-DBVisual Encoder=ViT-L/32, Time (ms)=1162024.090.9237————————————
Qwen-VL-chatType=LLM-based, Size=7B2024.010.923————————————
Qwen-VLType=Generalist2024.090.923————————————
LION-4BEvaluation Setting=Fine-tuning Setting2023.110.9229————————————
Qwen-VL-7B-ChatModel type=Generalist Models2023.080.9227————————————
Qwen-VLType=Generalist2024.030.9227————————————
Qwen-VLModel type=Generalist Models, Backbone=Qwen-7B2023.120.9227————————————
Qwen-VL-7BParameters=7B2024.020.9227————————————
UNITER_BASEdetected proposals=false, Model Scale=BASE2020.060.9226————————————
Qwen-VL-7BModel type=Generalist Models2023.080.9226————————————
Qwen-VLType=Generalist2023.110.9226————————————
Qwen-VL-7B2023.120.9226————————————
Qwen-VL-7BModel Size=7B2024.070.9226————————————