List your company

Multimodal Search on HR-MMSearch

48.52AccuracyGemini-3-Pro
-1.337611.606224.5537.4938Jun 4, 2026

Evaluation results

MethodLinks
Gemini-3-ProWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.0648.52
GPT-5.2Workflow=Agentic Model (zero-shot), Model Type=Proprietary2026.0648.2
Gemini-3-FlashWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.0641.64
TAPOWorkflow=Agentic Model, Model Type=Open-source, Backbone=SAPO2026.0640.66
SenseNova-MARSWorkflow=Agentic Model, Model Type=Open-source2026.0640.33
Gemini-2.5-FlashWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.0640
Qwen3-VL-8B-Instruct+SAPOWorkflow=Agentic Model, Model Type=Open-source2026.0638.69
GPT-5Workflow=Agentic Model (zero-shot), Model Type=Proprietary2026.0638.36
Qwen3-VL-32B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.0634.43
Qwen2.5-VL-32B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.0633.44
GPT-4oWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.0630.16
Qwen3-VL-8B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.0627.87
Gemini-3-ProWorkflow=Direct Answer, Model Type=Proprietary2026.0626.89
GPT-4o-miniWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.0626.23
GPT-5.2Workflow=Direct Answer, Model Type=Proprietary2026.0624.92
Visual-ARFTWorkflow=Agentic Model, Model Type=Open-source2026.0624.92
GPT-5Workflow=Direct Answer, Model Type=Proprietary2026.0622.62
Gemini-3-FlashWorkflow=Direct Answer, Model Type=Proprietary2026.0621.97
MMSearch-R1Workflow=Agentic Model, Model Type=Open-source2026.0620.33
Qwen2.5-VL-7B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.0619.34
Qwen3-VL-32B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.0619.02
GPT-4oWorkflow=Direct Answer, Model Type=Proprietary2026.0613.11
Qwen3-VL-8B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.0612.13
Gemini-2.5-FlashWorkflow=Direct Answer, Model Type=Proprietary2026.067.54
Qwen2.5-VL-32B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.063.93
GPT-4o-miniWorkflow=Direct Answer, Model Type=Proprietary2026.061.31
Qwen2.5-VL-7B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.060.58