List your company

Multimodal Question Answering on LiveVQA

70.5Pass@1OpenSearch-VL-32B
21.20434.00246.859.598May 6, 2026

Evaluation results

MethodLinks
OpenSearch-VL-32BWorkflow=Agentic Workflow2026.0570.5
OpenSearch-VL-30B-A3BWorkflow=Agentic Workflow2026.0567.4
Qwen3-VL-30B-A3BWorkflow=Agentic Workflow2026.0562
Gemini-2.5-ProWorkflow=Direct Reasoning2026.0560.3
OpenSearch-VL-8BWorkflow=Agentic Workflow2026.0559.6
WebWatcher-32BWorkflow=Agentic Workflow2026.0558.7
SenseNova-MARS-8BWorkflow=Agentic Workflow2026.0556.2
GPT-5Workflow=RAG Workflow2026.0556
WebWatcher-7BWorkflow=Agentic Workflow2026.0551.2
Gemini-2.5-FlashWorkflow=Direct Reasoning2026.0551
Qwen3-VL-8BWorkflow=Agentic Workflow2026.0550.6
MMSearch-R1-7BWorkflow=Agentic Workflow2026.0548.4
Qwen3-VL-32BWorkflow=Direct Reasoning2026.0545.5
Qwen3-VL-32BWorkflow=Agentic Workflow2026.0545.5
GPT-5Workflow=Direct Reasoning2026.0544.4
Qwen3-VL-30B-A3BWorkflow=Direct Reasoning2026.0542.7
GPT-4oWorkflow=RAG Workflow2026.0540.1
Qwen3-VL-8BWorkflow=RAG Workflow2026.0539.3
Claude-4-SonnetWorkflow=Direct Reasoning2026.0538.5
Claude-3.7-SonnetWorkflow=Direct Reasoning2026.0538
Claude-3.7-SonnetWorkflow=RAG Workflow2026.0530.3
GPT-4oWorkflow=Direct Reasoning2026.0528.1
Visual-ARFT-7BWorkflow=Agentic Workflow2026.0525.4
Qwen3-VL-8BWorkflow=Direct Reasoning2026.0523.1