Image Understanding on LLaVABenchWilder
77.9ScoreLLaVA-OneVision-7B w/ VL-MDR
Evaluation results
| Method | Links | |
|---|---|---|
| LLaVA-OneVision-7B w/ VL-MDRReward Model Paradigm=Discriminative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 77.9 | |
| LLaVA-OneVision-7B w/ Skywork-VLReward Model Paradigm=Discriminative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 77.6 | |
| LLaVA-OneVision-7B w/ UnifiedReward-ThinkReward Model Paradigm=Generative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 77.5 | |
| LLaVA-OneVision-7B w/ IXC-2.5-RewardReward Model Paradigm=Discriminative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 77 | |
| LLaVA-OneVision-7B w/ MM-RLHF-RewardReward Model Paradigm=Discriminative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 76.2 | |
| LLaVA-OneVision-7B w/ UnifiedRewardReward Model Paradigm=Generative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 75 | |
| LLaVA-OneVision-7B w/ LLaVA-CriticReward Model Paradigm=Generative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 71.6 | |
| LLaVA-OneVision-7BBase Model=LLaVA-OneVision-7B2026.04 | 67.8 |