List your company

Free-form Description Evaluation on EventHallusion

2.52LLM Likert ScoreVPS (J = 4)
1.91682.07342.232.3866Sep 9, 2025

Evaluation results

MethodLinks
VPS (J = 4)Model=Qwen2.5-VL-7B, Nframe=162025.092.5250.819.8
BaselineModel=Gemma3-12B, Nframe=82025.092.5148.717.3
BaselineModel=Qwen2.5-VL-7B, Nframe=82025.092.549.219.7
VPS (J = 4)Model=Gemma3-12B, Nframe=82025.092.4948.918.8
VPS (J = 4)Model=Qwen2.5-VL-7B, Nframe=42025.092.4748.719.5
VPS (J = 4)Model=Qwen2.5-VL-7B, Nframe=82025.092.4349.819.9
BaselineModel=Qwen2.5-VL-7B, Nframe=42025.092.414819.2
VPS (J = 4)Model=Gemma3-12B, Nframe=162025.092.448.518.5
VPS (J = 4)Model=InternVL3-8B, Nframe=82025.092.39459.24
VPS (J = 4)Model=InternVL3-8B, Nframe=162025.092.3344.89.29
BaselineModel=Gemma3-12B, Nframe=162025.092.3348.417.9
BaselineModel=InternVL3-8B, Nframe=82025.092.3439.26
BaselineModel=Gemma3-12B, Nframe=42025.092.2648.217.8
VPS (J = 4)Model=Qwen2.5-VL-7B, Nframe=22025.092.2546.119.8
BaselineModel=InternVL3-8B, Nframe=162025.092.2444.59.2
VPS (J = 4)Model=InternVL3-8B, Nframe=42025.092.23439.1
VPS (J = 4)Model=Gemma3-12B, Nframe=42025.092.2148.417.5
BaselineModel=InternVL3-8B, Nframe=42025.092.1842.19.14
VPS (J = 4)Model=InternVL3-8B, Nframe=22025.092.1443.79.89
BaselineModel=InternVL3-8B, Nframe=22025.092.0941.99.24
BaselineModel=Qwen2.5-VL-7B, Nframe=22025.092.0644.319.8
BaselineModel=Qwen2.5-VL-7B, Nframe=162025.092.0543.519.2
VPS (J = 4)Model=Gemma3-12B, Nframe=22025.092.0547.518.7
BaselineModel=Gemma3-12B, Nframe=22025.091.9445.818