Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human-AI Collaboration on Overcooked-AI (Evaluation partner population (novel AI behaviors))
Loading...
165.8
Cramped Room Score
PASD
28.52
64.16
99.8
135.44
May 23, 2026
Cramped Room Score
Asymmetric Advantages Score
Coordination Ring Score
Counter Circuit Score
Forced Coordination Score
Updated 8d ago
Evaluation Results
Method
Method
Links
Cramped Room Score
Asymmetric Advantages Score
Coordination Ring Score
Counter Circuit Score
Forced Coordination Score
PASD
Partner versions=Early...
2026.05
165.8
145.8
101.3
57.37
46.87
FCP
Partner versions=Early...
2026.05
137.7
90.6
83.9
51.3
36.7
HiPT
Partner versions=Early...
2026.05
117.9
86.2
96
38.1
35.6
DIAYN
Partner versions=Early...
2026.05
33.8
1.5
22.5
1.2
1.3
Feedback
Search any
task
Search any
task
