List your company

Hallucination Robustness on HallusionBench (fAcc)

37.3fAccQwen2.5-VL + DRScaffold
24.61227.90631.234.494May 25, 2026

Evaluation results

MethodLinks
Qwen2.5-VL + DRScaffoldScale=3B2026.0537.3
Qwen2.5-VLScale=3B2026.0535.2
Phi4-multimodal + DRScaffoldScale=5.6B2026.0534.4
InternVL2.5 + DRScaffoldScale=2B2026.0533.8
InternVL2.5Scale=2B2026.0532.6
Qwen2.5-VLScale=32B2026.0531.2
Phi4-multimodalScale=5.6B2026.0525.1