Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-agent coordination on TrafficJunction Small ablation (test)
Loading...
1
Task Success Rate
J-M
-0.04
0.23
0.5
0.77
May 13, 2026
Task Success Rate
Updated 20d ago
Evaluation Results
Method
Method
Links
Task Success Rate
J-M
Attack rate=0.75
2026.05
1
J-W
Attack rate=0.75
2026.05
1
J-M
Attack rate=0.25
2026.05
0
J-M
Attack rate=0.5
2026.05
0
J-W
Attack rate=0.25
2026.05
0
J-W
Attack rate=0.5
2026.05
0
CBTS
Attack rate=0.25
2026.05
0
CBTS
Attack rate=0.5
2026.05
0
CBTS
Attack rate=0.75
2026.05
0
MMR
Attack rate=0.25
2026.05
0
MMR
Attack rate=0.5
2026.05
0
MMR
Attack rate=0.75
2026.05
0
ML
Attack rate=0.25
2026.05
0
ML
Attack rate=0.5
2026.05
0
ML
Attack rate=0.75
2026.05
0
NS
Attack rate=0.25
2026.05
0
NS
Attack rate=0.5
2026.05
0
NS
Attack rate=0.75
2026.05
0
VL
Attack rate=0.25
2026.05
0
VL
Attack rate=0.5
2026.05
0
VL
Attack rate=0.75
2026.05
0
ST
Attack rate=0.25
2026.05
0
ST
Attack rate=0.5
2026.05
0
ST
Attack rate=0.75
2026.05
0
Feedback
Search any
task
Search any
task
