Skip to main content

Table 1 Performance on different benchmarks

From: Neutron: an attention-based neural decompiler

  Hacker’s Delight Karel CSmith Math NE Math+NE
Neutron 100% 100% 95.45% 98% 97.4% 97.00%
LSTM+attention 8.69% 81.05% 73% 80% 71.79% 56.67%
LSTM 0 0 21.7% 37% 31.66% 49.18%