List your company

Hallucination Benchmark on POPE-P

87.3AccuracyV-STAR
81.5883.06584.5586.035Apr 11, 2026

Evaluation results

MethodLinks
V-STARData Size=40k2026.0487.3
ThinkLite-VLData Size=11k2026.0486.7
Vision-R1Data Size=210k2026.0485.2
VL-CogitoData Size=80k2026.0485
R1-OnevisionData Size=155k2026.0484
Qwen2.5VL2026.0483.2
OpenVLThinkerData Size=59.2k2026.0482.5
VL-RethinkerData Size=39k2026.0481.8