List your company
ResearchFormerly WizWand

Hallucination Evaluation on AMBER-D

89.4ScoreQwen2.5-VL-32B
14.31233.80653.372.794Apr 1, 2026
Updated 7mo ago

Evaluation results

MethodLinks
Qwen2.5-VL-32BModel Scale=Large, Framework=Baseline, Visual Highlighting=false2026.0489.4
Qwen2.5-VL-32B + LoTModel Scale=Large, Framework=LoT, Visual Highlighting=true2026.0489
InternVL3.5-38B + LoTModel Scale=Large, Framework=LoT, Visual Highlighting=true2026.0482.5
Qwen3-VL-4BModel Scale=Small, Framework=Baseline, Visual Highlighting=false2026.0481.9
Qwen3-VL-4B + LoTModel Scale=Small, Framework=LoT, Visual Highlighting=true2026.0481.2
InternVL3.5-8B + LoTModel Scale=Medium, Framework=LoT, Visual Highlighting=true2026.0480.8
InternVL3.5-8BModel Scale=Medium, Framework=Baseline, Visual Highlighting=false2026.0480.4
InternVL3.5-4BModel Scale=Small, Framework=Baseline, Visual Highlighting=false2026.0480.1
InternVL3.5-38BModel Scale=Large, Framework=Baseline, Visual Highlighting=false2026.0479.8
Qwen3-VL-8BModel Scale=Medium, Framework=Baseline, Visual Highlighting=false2026.0475.9
Qwen2-VL-2B + LoTModel Scale=Small, Framework=LoT, Visual Highlighting=true2026.0475
InternVL3.5-4B + LoTModel Scale=Small, Framework=LoT, Visual Highlighting=true2026.0473
Qwen2.5-VL-7B + LoTModel Scale=Medium, Framework=LoT, Visual Highlighting=true2026.0462.6
Qwen3-VL-8B + LoTModel Scale=Medium, Framework=LoT, Visual Highlighting=true2026.0462.6
Qwen2.5-VL-7BModel Scale=Medium, Framework=Baseline, Visual Highlighting=false2026.0462
Qwen2-VL-7B + LoTModel Scale=Medium, Framework=LoT, Visual Highlighting=true2026.0447.3
Qwen2-VL-2BModel Scale=Small, Framework=Baseline, Visual Highlighting=false2026.0442.1
Qwen2.5-VL-3B + LoTModel Scale=Small, Framework=LoT, Visual Highlighting=true2026.0440.5
Qwen2-VL-7BModel Scale=Medium, Framework=Baseline, Visual Highlighting=false2026.0433.7
Qwen2.5-VL-3BModel Scale=Small, Framework=Baseline, Visual Highlighting=false2026.0417.2