Paper Reproduction on RE-Bench Weighted benchmark leaderboard · SOTA2 Research

Paper Reproduction on RE-Bench Weighted

93.2Success RateBaseline

Evaluation Results

Method	Links
Baseline2026.04		93.2
ARA2026.04		92.2
ARA2026.04		88.2
ARA2026.04		86.7
Baseline2026.04		85.3
ARA2026.04		76.2
ARA2026.04		72.8
Baseline2026.04		71.8
Baseline2026.04		71
ARA2026.04		69.9
Baseline2026.04		65.8
ARA2026.04		64.8
ARA2026.04		64.4
ARA2026.04		63.5
Baseline2026.04		60.4
Baseline2026.04		57.4
ARA2026.04		57.3
Baseline2026.04		55
ARA2026.04		53.2
ARA2026.04		49.8
Baseline2026.04		49.3
Baseline2026.04		48.9
Baseline2026.04		47.8
ARA2026.04		42.7
Baseline2026.04		42.3
Baseline2026.04		40.8
Baseline2026.04		38.8
ARA2026.04		38.2
ARA2026.04		35.1
Baseline2026.04		35
Baseline2026.04		34.4
ARA2026.04		33