List your company

Package Hallucination Evaluation on SO_LY

57.79Hallucination ASRNPA
6.684419.952233.2246.4878May 28, 2026

Evaluation results

MethodLinks
NPAModel=Gemma-3-12b-it2026.0557.7937.93
NPAModel=Nemotron-3-Nano-30B-A3B2026.0554.2922.02
NPA-StealthModel=Nemotron-3-Nano-30B-A3B2026.0552.1127.23
Normal SkillModel=Nemotron-3-Nano-30B-A3B2026.0550.221.71
IPModel=Nemotron-3-Nano-30B-A3B2026.0548.6919.05
NPAModel=Qwen2.5-Coder-32B-Instruct2026.0523.739.31
NPA-StealthModel=Gemma-3-12b-it2026.0519.2574.3
NPA-StealthModel=Qwen2.5-Coder-32B-Instruct2026.0517.1528.98
IPModel=Gemma-3-12b-it2026.0515.486.42
NPAModel=Qwen2.5-Coder-14B-Instruct2026.0515.324.84
Normal SkillModel=Gemma-3-12b-it2026.0514.953.05
Normal SkillModel=Qwen2.5-Coder-14B-Instruct2026.0514.770
IPModel=Qwen2.5-Coder-14B-Instruct2026.0514.320
NPA-StealthModel=Qwen2.5-Coder-14B-Instruct2026.0513.283.33
Normal SkillModel=Qwen2.5-Coder-32B-Instruct2026.059.483.11
IPModel=Qwen2.5-Coder-32B-Instruct2026.058.652.21