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

Multi-Agent Coordination on TJ environment (test)

100Max Success Rate

MAGIC

73.812880.611487.4194.2086Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
1001,144737,6371,537,315
2026.06
100474738,426771,422
2026.06
99.984721,312,5001,382,836
2026.06
99.913671,392,5101,477,974
2026.06
99.75868657,157699,102
2026.06
99.455011,872,7441,920,432
2026.06
98.28388936,721965,363
2026.06
97.481,294736,901773,801
2026.06
96.15828736,876772,184
2026.06
96.11231,471,5161,536,860
2026.06
91.571,067657,117765,237
2026.06
90.44492737,293832,487
2026.06
87.411,345656,786682,442
2026.06
78.87416937,246957,932
2026.06
74.82969657,197821,304