Share your thoughts, 1 month free Claude Pro on usSee more

Code Hallucination Detection on DS-1000

0.95OP

Pyright

Updated 9d ago

Evaluation Results

Method	Links
Pyright 2026.04		0.95	0.55	0.52
o3-mini 2026.04		0.79	0.51	0.68
Mypy 2026.04		0.63	0.26	0.21
o3-mini 2026.04		0.63	0.43	0.29
Pyright 2026.04		0.61	0.7	0.85
o3-mini 2026.04		0.61	0.45	0.29
Pyright 2026.04		0.57	0.6	0.75
Grammar 2026.04		0.57	0.1	0.17
o3-mini 2026.04		0.55	0.43	0.26
Grammar 2026.04		0.53	0.15	0.2
Pyright 2026.04		0.5	0.62	0.84
Grammar 2026.04		0.45	0.11	0.15
Grammar 2026.04		0.36	0.14	0.16
Mypy 2026.04		0.26	0.34	0.23
Mypy 2026.04		0.22	0.27	0.22
Mypy 2026.04		0.16	0.23	0.26