List your company
ResearchFormerly WizWand

Visual Search on V* Bench (Accuracy)

90.4AccuracyDeepeyes-7B
35.48849.7446478.256May 29, 2025Jul 16, 2025Sep 3, 2025Oct 22, 2025Dec 10, 2025Jan 28, 2026Mar 18, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Deepeyes-7BModel Category=Open-Source MLLMs with Tools, reproduced=true2025.1290.4
Multi-t ViGoRL-7BModel Category=Open-source Models2025.0586.4
Qwen2.5-VL-32BModel Category=Open-Source MLLMs2025.1285.9
Qwen2.5-VL-72BModel Category=Open-Source MLLMs2025.1284.8
CodeDance-7BModel Category=Open-Source MLLMs with Tools2025.1284.8
Pixel Reasoner-7BModel Category=Open-Source MLLMs with Tools2025.1284.3
Thyme-VL-7BModel Category=Open-Source MLLMs with Tools2025.1282.2
IVM-Enhanced GPT-4VModel Category=VLM Tool-Using Pipelines2025.0581.2
Multi-t ViGoRL-3BModel Category=Open-source Models2025.0581.2
Multi-t ViGoRL-3BModel Category=Open-source Models, configuration=w/ bounding box outputs2025.0581.2
Sketchpad-GPT-4oModel Category=VLM Tool-Using Pipelines2025.0580.3
ViGoRL-3B (Ours)Model Category=Open-source Models2025.0579.1
Qwen2.5-7B-VLModel Category=Open-source Models2025.0578
Multi-t ViGoRL-3BModel Category=Open-source Models, ablation=w/o diversity reward2025.0578
InternVL3-78BModel Category=Open-Source MLLMs2025.1276.4
Qwen2.5-VL-7BModel Category=Open-Source MLLMs2025.1276.4
SEALModel Category=Open-source Models2025.0574.8
Qwen2.5-3B-VLModel Category=Open-source Models2025.0574.2
Llava-OneVision-72BModel Category=Open-Source MLLMs2025.1273.8
InternVL2.5-8BModel Category=Open-Source MLLMs2025.1273.7
Qwen2.5-VL-7B +FINER-TuningBackbone=Qwen2.5-VL-7B, Training Strategy=FINER-Tuning2026.0372.8
Llava-OneVision-7BModel Category=Open-Source MLLMs2025.1272.7
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B2026.0372.7
InternVL3.5-8B +FINER-TuningBackbone=InternVL3.5-8B, Training Strategy=FINER-Tuning2026.0371.2
InternVL3-8BModel Category=Open-Source MLLMs2025.1270.2
InternVL3.5-14B +FINER-TuningBackbone=InternVL3.5-14B, Training Strategy=FINER-Tuning2026.0370.2
InternVL3.5-8BBackbone=InternVL3.5-8B2026.0369.1
InternVL3.5-14BBackbone=InternVL3.5-14B2026.0368
GPT-4oModel Category=Closed-Source MLLMs2025.1267.5
GPT-4oModel Category=Proprietary Models2025.0566
LLaVA-1.6-13BModel Category=Open-source Models2025.0561.8
LLaVA-1.6-7B +FINER-TuningBackbone=LLaVA-1.6-7B, Training Strategy=FINER-Tuning2026.0355
GPT-4VModel Category=Proprietary Models2025.0555
OmniLMM-12B +RLAIF-VBackbone=OmniLMM-12B, Training Strategy=RLAIF-V2026.0354.4
LLaVA-1.6-7BBackbone=LLaVA-1.6-7B2026.0353.9
OmniLMM-12BBackbone=OmniLMM-12B2026.0352.9
LLaVA-1.5-7BModel Category=Open-source Models2025.0548.7
Gemini-ProModel Category=Proprietary Models2025.0548.2
VisProgModel Category=VLM Tool-Using Pipelines2025.0541.4
MM-ReactModel Category=VLM Tool-Using Pipelines2025.0541.4
VisualChatGPTModel Category=VLM Tool-Using Pipelines2025.0537.6