List your company

Video Search Question Answering on VSQA

65.11ScoreGemini-3-Pro
6.745221.897637.0552.2024Jul 3, 2026

Evaluation results

MethodLinks
Gemini-3-ProWorkflow=Agentic Model, Zero-shot=true2026.0765.11
Gemini-3-FlashWorkflow=Agentic Model, Zero-shot=true2026.0758.99
GPT-5.2Workflow=Agentic Model, Zero-shot=true2026.0757.19
Gemini-3-FlashWorkflow=Direct Answer, Zero-shot=false2026.0756.12
Gemini-3-ProWorkflow=Direct Answer, Zero-shot=false2026.0754.32
VideoSearcher-8BWorkflow=Agentic Model, Zero-shot=false2026.0751.8
GPT-4oWorkflow=Agentic Model, Zero-shot=true2026.0749.64
VideoSearcher-4BWorkflow=Agentic Model, Zero-shot=false2026.0749.28
GPT-5.2Workflow=Direct Answer, Zero-shot=false2026.0738.85
Qwen3-VL-32B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0737.77
GPT-4oWorkflow=Direct Answer, Zero-shot=false2026.0736.33
Webwatcher-7BWorkflow=Agentic Model, Zero-shot=false2026.0734.53
Qwen3-VL-8B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0730.94
Qwen3-VL-4B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0729.14
Qwen2.5-VL-32B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0729.14
DeepEyesV2Workflow=Agentic Model, Zero-shot=false2026.0721.58
Qwen3-VL-32B-InstructWorkflow=Direct Answer, Zero-shot=false2026.0720.86
Qwen3-VL-8B-InstructWorkflow=Direct Answer, Zero-shot=false2026.0716.91
Qwen2.5-VL-32B-InstructWorkflow=Direct Answer, Zero-shot=false2026.0713.67
Qwen3-VL-4B-InstructWorkflow=Direct Answer, Zero-shot=false2026.0712.59
MMSearch-R1Workflow=Agentic Model, Zero-shot=false2026.0711.87
Qwen2.5-VL-7B-InstructWorkflow=Agentic Model, Zero-shot=true2026.0711.15
Qwen2.5-VL-7B-InstructWorkflow=Direct Answer, Zero-shot=false2026.079.35
Visual-ARFTWorkflow=Agentic Model, Zero-shot=false2026.078.99