Multimodal Search on HR-MMSearch
48.52AccuracyGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-ProWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 48.52 | |
| GPT-5.2Workflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 48.2 | |
| Gemini-3-FlashWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 41.64 | |
| TAPOWorkflow=Agentic Model, Model Type=Open-source, Backbone=SAPO2026.06 | 40.66 | |
| SenseNova-MARSWorkflow=Agentic Model, Model Type=Open-source2026.06 | 40.33 | |
| Gemini-2.5-FlashWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 40 | |
| Qwen3-VL-8B-Instruct+SAPOWorkflow=Agentic Model, Model Type=Open-source2026.06 | 38.69 | |
| GPT-5Workflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 38.36 | |
| Qwen3-VL-32B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.06 | 34.43 | |
| Qwen2.5-VL-32B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.06 | 33.44 | |
| GPT-4oWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 30.16 | |
| Qwen3-VL-8B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.06 | 27.87 | |
| Gemini-3-ProWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 26.89 | |
| GPT-4o-miniWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 26.23 | |
| GPT-5.2Workflow=Direct Answer, Model Type=Proprietary2026.06 | 24.92 | |
| Visual-ARFTWorkflow=Agentic Model, Model Type=Open-source2026.06 | 24.92 | |
| GPT-5Workflow=Direct Answer, Model Type=Proprietary2026.06 | 22.62 | |
| Gemini-3-FlashWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 21.97 | |
| MMSearch-R1Workflow=Agentic Model, Model Type=Open-source2026.06 | 20.33 | |
| Qwen2.5-VL-7B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.06 | 19.34 | |
| Qwen3-VL-32B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.06 | 19.02 | |
| GPT-4oWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 13.11 | |
| Qwen3-VL-8B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.06 | 12.13 | |
| Gemini-2.5-FlashWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 7.54 | |
| Qwen2.5-VL-32B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.06 | 3.93 | |
| GPT-4o-miniWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 1.31 | |
| Qwen2.5-VL-7B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.06 | 0.58 |