Visual Information Seeking on InfoSeek
74.8Pass@1OpenSearch-VL-32B
Evaluation Results
| Method | Links | |
|---|---|---|
| OpenSearch-VL-32BWorkflow=Agentic Workflow2026.05 | 74.8 | |
| OpenSearch-VL-30B-A3BWorkflow=Agentic Workflow2026.05 | 72.4 | |
| GPT-5Workflow=RAG Workflow2026.05 | 70.6 | |
| OpenSearch-VL-8BWorkflow=Agentic Workflow2026.05 | 70.2 | |
| GPT-5Workflow=Direct Reasoning2026.05 | 61.7 | |
| SenseNova-MARS-8BWorkflow=Agentic Workflow2026.05 | 61.7 | |
| Claude-3.7-SonnetWorkflow=RAG Workflow2026.05 | 60.2 | |
| GPT-4oWorkflow=RAG Workflow2026.05 | 59.5 | |
| Qwen3-VL-32BWorkflow=Agentic Workflow2026.05 | 58.5 | |
| Claude-4-SonnetWorkflow=Direct Reasoning2026.05 | 57.3 | |
| Qwen3-VL-30B-A3BWorkflow=Agentic Workflow2026.05 | 56.2 | |
| MMSearch-R1-7BWorkflow=Agentic Workflow2026.05 | 55.1 | |
| Claude-3.7-SonnetWorkflow=Direct Reasoning2026.05 | 54.8 | |
| GPT-4oWorkflow=Direct Reasoning2026.05 | 52.9 | |
| DeepEyes-v2-7BWorkflow=Agentic Workflow2026.05 | 51.1 | |
| Qwen3-VL-8BWorkflow=Agentic Workflow2026.05 | 50.3 | |
| DeepMMSearch-R1-7BWorkflow=Agentic Workflow2026.05 | 47.5 | |
| Gemini-2.5-ProWorkflow=Direct Reasoning2026.05 | 46.9 | |
| Qwen3-VL-8BWorkflow=RAG Workflow2026.05 | 46.1 | |
| Gemini-2.5-FlashWorkflow=Direct Reasoning2026.05 | 44.1 | |
| Visual-ARFT-7BWorkflow=Agentic Workflow2026.05 | 37.9 | |
| Qwen3-VL-32BWorkflow=Direct Reasoning2026.05 | 28.8 | |
| Qwen3-VL-30B-A3BWorkflow=Direct Reasoning2026.05 | 26.4 | |
| Qwen3-VL-8BWorkflow=Direct Reasoning2026.05 | 23.1 |