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

Long-horizon cascade synthesis on PBEBench Hard

85.8Accuracy

BoK + All Symbolic

22.46438.90755.3571.793May 6, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
85.80.95792.74.64
2026.05
84.70.99298.64.56
2026.05
83.50.953191.95.48
2026.05
81.20.990598.35.35
2026.05
80.70.949691.35.48
2026.05
79.40.950891.47.82
2026.05
74.70.983696.85.26
2026.05
69.70.987397.28.06
2026.05
68.40.942889.95.14
2026.05
24.90.841173.21.36