List your company

Aerial Visual Reasoning on AerialVP

90.48AccuracyQwen2.5-Max
44.886456.723268.5680.3968Dec 8, 2025

Evaluation results

MethodLinks
Qwen2.5-MaxSemantic Enhancement=true, Spatial Relationship Enhancement=true2025.1290.48
LLaVA-1.5-7BSemantic Enhancement=true, Spatial Relationship Enhancement=true2025.1290.44
Gemini-2.0Semantic Enhancement=true, Spatial Relationship Enhancement=true2025.1290.4
GPT-4.1Semantic Enhancement=true, Spatial Relationship Enhancement=true2025.1290.32
Qwen2-VL-7BSemantic Enhancement=true, Spatial Relationship Enhancement=true2025.1285.6
Claude-3.7Semantic Enhancement=true, Spatial Relationship Enhancement=true2025.1285.48
LLaVA-OneVision-7BSemantic Enhancement=true, Spatial Relationship Enhancement=true2025.1283.91
GPT-4oSemantic Enhancement=true, Spatial Relationship Enhancement=true2025.1280.71
InternVL3-14BSemantic Enhancement=true, Spatial Relationship Enhancement=true2025.1280.3
InternVL3-8BSemantic Enhancement=true, Spatial Relationship Enhancement=true2025.1278.85
Qwen2.5-MaxSemantic Enhancement=false, Spatial Relationship Enhancement=false2025.1277.03
Gemini-2.0Semantic Enhancement=false, Spatial Relationship Enhancement=false2025.1275.65
SAILVL-8BSemantic Enhancement=true, Spatial Relationship Enhancement=true2025.1273.84
GPT-4.1Semantic Enhancement=false, Spatial Relationship Enhancement=false2025.1270.4
LLaVA-OneVision-7BSemantic Enhancement=false, Spatial Relationship Enhancement=false2025.1269.48
InternVL3-14BSemantic Enhancement=false, Spatial Relationship Enhancement=false2025.1263.22
Claude-3.7Semantic Enhancement=false, Spatial Relationship Enhancement=false2025.1262.78
InternVL3-8BSemantic Enhancement=false, Spatial Relationship Enhancement=false2025.1256.6
Qwen2-VL-7BSemantic Enhancement=false, Spatial Relationship Enhancement=false2025.1256.4
LLaVA-1.5-7BSemantic Enhancement=false, Spatial Relationship Enhancement=false2025.1253.89
GPT-4oSemantic Enhancement=false, Spatial Relationship Enhancement=false2025.1250.72
SAILVL-8BSemantic Enhancement=false, Spatial Relationship Enhancement=false2025.1246.64