Package Hallucination Evaluation on LLM_LY
78.99Hallucination ASRNPA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| NPAModel=Qwen2.5-Coder-32B-Instruct2026.05 | 78.99 | 63.33 | |
| NPAModel=Nemotron-3-Nano-30B-A3B2026.05 | 56.98 | 41.67 | |
| NPA-StealthModel=Nemotron-3-Nano-30B-A3B2026.05 | 39.38 | 59.6 | |
| IPModel=Nemotron-3-Nano-30B-A3B2026.05 | 38.24 | 23.97 | |
| Normal SkillModel=Nemotron-3-Nano-30B-A3B2026.05 | 35.58 | 34.46 | |
| NPAModel=Qwen2.5-Coder-14B-Instruct2026.05 | 25.9 | 25.93 | |
| NPAModel=Gemma-3-12b-it2026.05 | 16.76 | 38.18 | |
| NPA-StealthModel=Gemma-3-12b-it2026.05 | 11.26 | 66.49 | |
| IPModel=Gemma-3-12b-it2026.05 | 10.44 | 20.48 | |
| NPA-StealthModel=Qwen2.5-Coder-32B-Instruct2026.05 | 9.85 | 27.72 | |
| Normal SkillModel=Gemma-3-12b-it2026.05 | 9.82 | 13.04 | |
| NPA-StealthModel=Qwen2.5-Coder-14B-Instruct2026.05 | 6.92 | 29.19 | |
| IPModel=Qwen2.5-Coder-14B-Instruct2026.05 | 6.51 | 0 | |
| Normal SkillModel=Qwen2.5-Coder-14B-Instruct2026.05 | 5.84 | 7.14 | |
| Normal SkillModel=Qwen2.5-Coder-32B-Instruct2026.05 | 4.54 | 6.65 | |
| IPModel=Qwen2.5-Coder-32B-Instruct2026.05 | 4.25 | 5.81 |