List your company

Code Hallucination Detection on BigCode

0.77OPo3-mini
0.13560.30030.4650.6297Apr 9, 2026

Evaluation results

MethodLinks
o3-miniQuery Model=Granite2026.040.770.480.5
o3-miniQuery Model=claude-32026.040.640.120.15
PyrightQuery Model=Granite2026.040.620.30.36
o3-miniQuery Model=gpt-42026.040.570.110.14
o3-miniQuery Model=gpt-3.52026.040.560.160.14
MypyQuery Model=Granite2026.040.470.090.1
GrammarQuery Model=Granite2026.040.450.090.06
PyrightQuery Model=gpt-42026.040.340.20.24
PyrightQuery Model=claude-32026.040.320.20.24
PyrightQuery Model=gpt-3.52026.040.280.160.14
MypyQuery Model=gpt-42026.040.240.090.08
GrammarQuery Model=gpt-3.52026.040.240.120.11
GrammarQuery Model=gpt-42026.040.230.060.06
MypyQuery Model=gpt-3.52026.040.220.070.03
GrammarQuery Model=claude-32026.040.190.040.06
MypyQuery Model=claude-32026.040.160.050.03