List your company

General Multimodal Performance on POPE, HallusionBench, MMStar Average

69.3Overall ScorePStar
48.08453.59259.164.608May 19, 2026

Evaluation results

MethodLinks
PStarBackbone=Qwen2.5-VL-7B2026.0569.3
PStarBackbone=Qwen2-VL-7B2026.0569
Qwen2.5-VL-7BModel=Qwen2.5-VL-7B*2026.0567.3
Qwen2-VL-7BModel=Qwen2-VL-7B*2026.0566.5
InternVL2-8BModel=InternVL2-8B*2026.0563.6
PStarBackbone=Qwen2-VL-2B2026.0560.8
GPT-4V (0409)Model=GPT-4V (0409)*2026.0560.6
Qwen2-VL-2BModel=Qwen2-VL-2B*2026.0559.5
LLaMA-3.2-11B-VisionModel=LLaMA-3.2-11B-Vision*2026.0559.4
InternVL2-2BModel=InternVL2-2B*2026.0557.7
LLaVA-v1.5-7BModel=LLaVA-v1.5-7B*2026.0548.9