Image Understanding on LLaVABench
101.9ScoreLLaVA-OneVision-7B w/ Skywork-VL
Evaluation results
| Method | Links | |
|---|---|---|
| LLaVA-OneVision-7B w/ Skywork-VLReward Model Paradigm=Discriminative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 101.9 | |
| LLaVA-OneVision-7B w/ VL-MDRReward Model Paradigm=Discriminative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 101.9 | |
| LLaVA-OneVision-7B w/ UnifiedReward-ThinkReward Model Paradigm=Generative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 101.8 | |
| LLaVA-OneVision-7B w/ IXC-2.5-RewardReward Model Paradigm=Discriminative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 101.6 | |
| LLaVA-OneVision-7B w/ UnifiedRewardReward Model Paradigm=Generative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 101.4 | |
| LLaVA-OneVision-7B w/ MM-RLHF-RewardReward Model Paradigm=Discriminative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 101.4 | |
| LLaVA-OneVision-7B w/ LLaVA-CriticReward Model Paradigm=Generative, Base Model=LLaVA-OneVision-7B, Alignment Method=DPO2026.04 | 100.3 | |
| LLaVA-OneVision-7BBase Model=LLaVA-OneVision-7B2026.04 | 90.3 |