List your company

Visual Question Answering on SimpleVQA (Score)

79.6ScoreSimpleSearch-VL-30B-A3B
40.44450.609560.77570.9405Jun 30, 2026Jul 1, 2026Jul 2, 2026Jul 3, 2026

Evaluation results

MethodLinks
SimpleSearch-VL-30B-A3BEvaluation Paradigm=Multimodal Search Agents2026.0679.6
GPT-5.2Workflow=Agentic Model, Zero-shot=true2026.0778.18
SimpleSearch-VL-8BEvaluation Paradigm=Multimodal Search Agents2026.0676.6
Gemini-3-ProWorkflow=Agentic Model, Zero-shot=true2026.0775.91
OpenSearch-VL-30B-A3BEvaluation Paradigm=Multimodal Search Agents2026.0674.9
OpenSearch-VL-8BEvaluation Paradigm=Multimodal Search Agents2026.0671.6
SenseNova-MARS-8BEvaluation Paradigm=Multimodal Search Agents2026.0670.2
POINTS-Seeker-8BEvaluation Paradigm=Multimodal Search Agents2026.0668.8
Gemini-3-FlashWorkflow=Agentic Model, Zero-shot=true2026.0767.92
VideoSearcher-8BWorkflow=Agentic Model, Zero-shot=false2026.0767.2
Qwen3-VL-30B-A3BEvaluation Paradigm=Agentic Workflow2026.0666.6
MM-DeepResearch-8BEvaluation Paradigm=Multimodal Search Agents2026.0665.9
VideoSearcher-4BWorkflow=Agentic Model, Zero-shot=false2026.0765.84
Qwen2.5-VL-32B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0765.15
Qwen3-VL-32B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0764.17
Gemini-3-ProWorkflow=Direct Answer, Zero-shot=false2026.0764.07
GPT-4oWorkflow=Agentic Model, Zero-shot=true2026.0763.67
Gemini-3-FlashWorkflow=Direct Answer, Zero-shot=false2026.0763.57
Qwen3-VL-8BEvaluation Paradigm=Agentic Workflow2026.0663.4
Qwen3-VL-8B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0762.29
GPT-5.2Workflow=Direct Answer, Zero-shot=false2026.0759.92
DeepEyesV2-7BEvaluation Paradigm=Multimodal Search Agents2026.0659.4
DeepEyesV2Workflow=Agentic Model, Zero-shot=false2026.0759.4
WebWatcher-32BEvaluation Paradigm=Multimodal Search Agents2026.0659
MMSearch-R1-7BEvaluation Paradigm=Multimodal Search Agents2026.0657.4
MMSearch-R1Workflow=Agentic Model, Zero-shot=false2026.0757.4
Webwatcher-7BWorkflow=Agentic Model, Zero-shot=false2026.0754.3
Qwen3-VL-30B-A3BEvaluation Paradigm=Direct Answer2026.0653.2
GPT-4oWorkflow=Direct Answer, Zero-shot=false2026.0751.73
Qwen2.5-VL-32B-InstructWorkflow=Direct Answer, Zero-shot=false2026.0748.57
Qwen2.5-VL-7B-InstructWorkflow=Direct Answer, Zero-shot=false2026.0747.88
Qwen3-VL-4B-InstructWorkflow=Direct Answer, Zero-shot=false2026.0746.89
Qwen3-VL-32B-InstructWorkflow=Direct Answer, Zero-shot=false2026.0745.9
Qwen3-VL-8B-InstructWorkflow=Direct Answer, Zero-shot=false2026.0742.94
Qwen3-VL-8BEvaluation Paradigm=Direct Answer2026.0642.9
Visual-ARFTWorkflow=Agentic Model, Zero-shot=false2026.0742.45
Qwen2.5-VL-7B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0742.35
Qwen3-VL-4B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0741.95