Hallucination Detection on HallucinationBench_image
68.8AccuracyPLM-HoneyBee-8B
Evaluation results
| Method | Links | |
|---|---|---|
| PLM-HoneyBee-8BModel scale=7B-8B2025.10 | 68.8 | |
| Qwen2.5-VL-7B-InstructModel scale=7B-8B2025.10 | 67.4 | |
| Qwen2.5-VL-3B-InstructModel scale=3B-4B2025.10 | 66 | |
| InternVL-2.5-4BModel scale=3B-4B2025.10 | 65.5 | |
| InternVL-3-8B-InstructModel scale=7B-8B2025.10 | 65.5 | |
| PLM-HoneyBee-3BModel scale=3B-4B2025.10 | 65 | |
| PLM-8BModel scale=7B-8B2025.10 | 64 | |
| InternVL-2.5-8BModel scale=7B-8B2025.10 | 63.8 | |
| PLM-3BModel scale=3B-4B2025.10 | 61.1 | |
| Qwen3-VL-8B2026.07 | 61.1 | |
| AutoTool-7BModel scale=7B2026.05 | 60.9 | |
| InternVL3-8BModel scale=8B2026.05 | 59.7 | |
| Qwen3-VL-8B + Qwen3-8B / H-OPDStudent=Qwen3-VL-4B-Instruct2026.07 | 59.3 | |
| DeepEyes-7BModel scale=7B2026.05 | 58.5 | |
| Qwen2.5-VL-7BModel scale=7B2026.05 | 57.8 | |
| PLM-HoneyBee-1BModel scale=1B2025.10 | 56.1 | |
| InternVL-3-1B-InstructModel scale=1B2025.10 | 56 | |
| LLaVA-OneVision-7BModel scale=7B2026.05 | 52.9 | |
| InternVL-2.5-1BModel scale=1B2025.10 | 51.6 | |
| PLM-1BModel scale=1B2025.10 | 50.3 |