Alignment on HalluBench
63AccuracyEVE (Ours-8B-iter4)
Evaluation results
| Method | Links | |
|---|---|---|
| EVE (Ours-8B-iter4)Model Category=Pseudo-label-based Self-evolution Methods, Scale=8B, Iteration=42026.04 | 63 | |
| Jigsaw-R1-8BModel Category=Template-based Self-evolution Methods, Scale=8B2026.04 | 62.1 | |
| MM-Zero-8B-iter3Model Category=Pseudo-label-based Self-evolution Methods, Scale=8B, Iteration=32026.04 | 61.7 | |
| VisPlay-8B-iter3Model Category=Pseudo-label-based Self-evolution Methods, Scale=8B, Iteration=32026.04 | 61.6 | |
| Qwen3-VL-8B-InstructModel Category=Open-Source MLLMs, Scale=8B2026.04 | 61.2 | |
| GPT-4o-20240513Model Category=Closed-Source MLLMs2026.04 | 55 | |
| Qwen-ViPER-7BModel Category=Pseudo-label-based Self-evolution Methods, Scale=7B2026.04 | 54.4 | |
| Spatial-SSRL-7BModel Category=Template-based Self-evolution Methods, Scale=7B2026.04 | 53.2 | |
| InternVL3-9BModel Category=Open-Source MLLMs, Scale=9B2026.04 | 51.2 | |
| LLaVA-OneVision-72BModel Category=Open-Source MLLMs, Scale=72B2026.04 | 49 |