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

Multi-Agent System Performance on Database

71.72Task Success Rate (TS)

MARBLE

66.811268.085669.3670.6344Mar 27, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
71.7269.1569.68
2026.03
71.5970.3971.38
2026.03
71.4373.2371.2
2026.03
7182.475.55
2026.03
7181.0776.2
2026.03
7166.0767.87
2026.03
70.4168.5569.98
2026.03
70.4176.1871.06
2026.03
7088.2778.52
2026.03
7075.672.62
2026.03
69.782.9675.7
2026.03
69.782.3175.13
2026.03
69.3988.0377.35
2026.03
6972.3267.61
2026.03
68.6973.4870.51
2026.03
6768.5364.38