List your company

Knowledge boundary assessment on V-Idk 3,000 samples (test)

51.9IK-IKDPO
26.52433.11239.746.288Apr 29, 2026

Evaluation results

MethodLinks
DPOModel=LLaVA-1.5 7B, Setting=Zero-shot2026.0451.95.557.4
DPOModel=LLaVA-1.5 13B, Setting=Zero-shot2026.0450.26.756.9
BaseModel=LLaVA-1.5 13B, Setting=Zero-shot2026.0449.94.354.2
DPOModel=LLaVA-1.5 13B, Setting=Few-shot2026.0449.721.471.1
BaseModel=LLaVA-1.5 13B, Setting=Few-shot2026.0449.619.869.4
ORPOModel=LLaVA-1.5 7B, Setting=Zero-shot2026.0445.914.160
BaseModel=LLaVA-1.5 7B, Setting=Zero-shot2026.0445.81.847.6
ORPOModel=LLaVA-1.5 13B, Setting=Zero-shot2026.0445.820.466.2
BaseModel=LLaVA-1.5 7B, Setting=Few-shot2026.0445.512.457.9
DPOModel=LLaVA-1.5 7B, Setting=Few-shot2026.0445.317.863.1
CPOModel=LLaVA-1.5 13B, Setting=Zero-shot2026.0444.91963.9
CPOModel=LLaVA-1.5 7B, Setting=Zero-shot2026.0444.413.958.3
CPOModel=LLaVA-1.5 13B, Setting=Few-shot2026.0443.730.374
CPOModel=LLaVA-1.5 7B, Setting=Few-shot2026.0442.824.567.3
ORPOModel=LLaVA-1.5 13B, Setting=Few-shot2026.0442.733.976.6
ORPOModel=LLaVA-1.5 7B, Setting=Few-shot2026.044026.566.5
SFTModel=LLaVA-1.5 7B, Setting=Zero-shot2026.0434.432.767.1
SFTModel=LLaVA-1.5 13B, Setting=Zero-shot2026.0434.439.173.5
SFTModel=LLaVA-1.5 7B, Setting=Few-shot2026.0427.636.864.4
SFTModel=LLaVA-1.5 13B, Setting=Few-shot2026.0427.539.867.3