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

Regret assessment on PDEBench RDB full-oracle case-level

-0.9Regret Knee

System-core

Updated 4mo ago

Evaluation Results

Method	Links
System-core 2026.03		-0.9
Direct-3-Shortlist 2026.03		-0.9
Direct-3-Shortlist 2026.03		0
Direct-4-Shortlist 2026.03		0
SAKE 2026.03		0
Direct-3-Shortlist 2026.03		0
Direct-4-Shortlist 2026.03		0
SAKE 2026.03		0
SAKE 2026.03		0
Direct-4-Shortlist 2026.03		36.4
System-core 2026.03		45
Direct-3-Shortlist 2026.03		47.2
Direct-4-Shortlist 2026.03		47.2
SAKE 2026.03		47.2
System-core 2026.03		113.8
System-core 2026.03		169