List your company

Visual Information Retrieval and Reasoning on ViDoSeek

74.87Overall AccuracyVISOR
7.363624.889342.41559.9407Apr 10, 2026

Evaluation results

MethodLinks
VISORBackbone=Qwen2.5-VL-7B, Multi-agent architecture=false, Fine-tuned=true2026.0474.8773.4976.66
EVisRAGBackbone=Qwen2.5-VL-7B, Multi-agent architecture=false, Fine-tuned=true2026.0469.7967.7572.43
M3RAGBackbone=Qwen2.5-VL-7B, Multi-agent architecture=true, Fine-tuned=false, External Source=Published results2026.0469.36——
ViDoRAGBackbone=Qwen2.5-VL-7B, Multi-agent architecture=true, Fine-tuned=false2026.046966.0572.83
VISORBackbone=Qwen2.5-VL-3B, Multi-agent architecture=false, Fine-tuned=true2026.046967.7570.62
EVisRAGBackbone=Qwen2.5-VL-3B, Multi-agent architecture=false, Fine-tuned=true2026.0468.8266.0572.43
VRAG-RLBackbone=Qwen2.5-VL-3B, Multi-agent architecture=false, Fine-tuned=true, External Source=Published results2026.0467.7663.173.8
VRAG-RLBackbone=Qwen2.5-VL-7B, Multi-agent architecture=false, Fine-tuned=true, External Source=Published results2026.0466.7860.674.8
R1-RouterBackbone=Qwen2.5-VL-7B, Multi-agent architecture=false, Fine-tuned=true2026.0466.1164.1968.61
R1-RouterBackbone=Qwen2.5-VL-3B, Multi-agent architecture=false, Fine-tuned=true2026.0465.5962.6469.42
MMSearch-R1Backbone=Qwen2.5-VL-7B, Multi-agent architecture=false, Fine-tuned=true2026.0457.5355.9759.56
Search-R1-VLBackbone=Qwen2.5-VL-7B, Multi-agent architecture=false, Fine-tuned=true, External Source=Published results2026.0444.7740.550.3
ViDoRAGBackbone=Qwen2.5-VL-3B, Multi-agent architecture=true, Fine-tuned=false2026.0434.3331.3238.23
ReActBackbone=Qwen2.5-VL-7B, Multi-agent architecture=false, Fine-tuned=false, External Source=Published results2026.0433.8527.542.1
Vanilla RAGBackbone=Qwen2.5-VL-7B, Multi-agent architecture=false, Fine-tuned=false, External Source=Published results2026.0432.8826.441.3
Search-R1-VLBackbone=Qwen2.5-VL-3B, Multi-agent architecture=false, Fine-tuned=true, External Source=Published results2026.0424.3220.129.8
Vanilla RAGBackbone=Qwen2.5-VL-3B, Multi-agent architecture=false, Fine-tuned=false, External Source=Published results2026.0413.2310.117.3
ReActBackbone=Qwen2.5-VL-3B, Multi-agent architecture=false, Fine-tuned=false, External Source=Published results2026.049.966.714.2