Multimodal Information Seeking on InfoSeek
66.45AccuracyGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-ProWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 66.45 | |
| GPT-5.2Workflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 65.55 | |
| TAPOWorkflow=Agentic Model, Model Type=Open-source, Backbone=SAPO2026.06 | 62.7 | |
| SenseNova-MARSWorkflow=Agentic Model, Model Type=Open-source2026.06 | 61.7 | |
| Gemini-3-FlashWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 61.1 | |
| GPT-4oWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 59.55 | |
| Qwen3-VL-8B-Instruct+SAPOWorkflow=Agentic Model, Model Type=Open-source2026.06 | 59.55 | |
| Gemini-3-ProWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 56.3 | |
| GPT-5Workflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 55.95 | |
| MMSearch-R1Workflow=Agentic Model, Model Type=Open-source2026.06 | 55.1 | |
| Gemini-3-FlashWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 54.85 | |
| GPT-5Workflow=Direct Answer, Model Type=Proprietary2026.06 | 54.15 | |
| Gemini-2.5-FlashWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 53.7 | |
| GPT-4oWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 52.9 | |
| DeepEyesV2Workflow=Agentic Model, Model Type=Open-source2026.06 | 51.1 | |
| GPT-5.2Workflow=Direct Answer, Model Type=Proprietary2026.06 | 50.4 | |
| Qwen2.5-VL-32B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.06 | 50.1 | |
| Qwen3-VL-32B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.06 | 49.85 | |
| DeepMMSearch-R1Workflow=Agentic Model, Model Type=Open-source2026.06 | 47.51 | |
| Qwen3-VL-8B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.06 | 46.15 | |
| Gemini-2.5-FlashWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 44.1 | |
| GPT-4o-miniWorkflow=Agentic Model (zero-shot), Model Type=Proprietary2026.06 | 42.35 | |
| Visual-ARFTWorkflow=Agentic Model, Model Type=Open-source2026.06 | 37.95 | |
| Qwen2.5-VL-32B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.06 | 36.65 | |
| GPT-4o-miniWorkflow=Direct Answer, Model Type=Proprietary2026.06 | 35.95 | |
| Qwen2.5-VL-7B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.06 | 31.95 | |
| Qwen3-VL-32B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.06 | 28.95 | |
| Qwen2.5-VL-7B-InstructWorkflow=Agentic Model (zero-shot), Model Type=Open-source2026.06 | 28.8 | |
| Qwen3-VL-8B-InstructWorkflow=Direct Answer, Model Type=Open-source2026.06 | 23.15 |