List your company

Package Hallucination Evaluation on SO_AT

71.99Hallucination ASRNPA
1.16619.55337.9456.327May 28, 2026

Evaluation results

MethodLinks
NPAModel=Nemotron-3-Nano-30B-A3B2026.0571.9923.33
NPAModel=Gemma-3-12b-it2026.0545.749.88
Normal SkillModel=Nemotron-3-Nano-30B-A3B2026.0544.816.94
IPModel=Nemotron-3-Nano-30B-A3B2026.0543.4813.92
NPA-StealthModel=Nemotron-3-Nano-30B-A3B2026.0541.2529.26
NPAModel=Qwen2.5-Coder-32B-Instruct2026.0537.9874.46
NPA-StealthModel=Gemma-3-12b-it2026.0516.3872.53
NPA-StealthModel=Qwen2.5-Coder-32B-Instruct2026.0511.3521.56
Normal SkillModel=Gemma-3-12b-it2026.058.985.36
NPAModel=Qwen2.5-Coder-14B-Instruct2026.058.893.17
NPA-StealthModel=Qwen2.5-Coder-14B-Instruct2026.058.514.29
IPModel=Gemma-3-12b-it2026.058.132.7
Normal SkillModel=Qwen2.5-Coder-14B-Instruct2026.057.363.17
IPModel=Qwen2.5-Coder-14B-Instruct2026.056.590
Normal SkillModel=Qwen2.5-Coder-32B-Instruct2026.054.682.4
IPModel=Qwen2.5-Coder-32B-Instruct2026.053.892.96