Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
N-Back Performance
Loading...
0.887
Human-Model Similarity (1 - NWD)
TASKPR
-0.11036
0.14857
0.4075
0.66643
May 25, 2026
Human-Model Similarity (1 - NWD)
Updated 8d ago
Evaluation Results
Method
Method
Links
Human-Model Similarity (1 - NWD)
TASKPR
Model Backbone=Claude...
2026.05
0.887
TASKPR
Model Backbone=Llama 3 8B
2026.05
0.855
COMPACTOR
Model Backbone=Llama 3...
2026.05
0.524
TASKPR
Model Backbone=Llama 3...
2026.05
0.451
MEMPR
Model Backbone=Llama 3...
2026.05
0.379
HUMPR
Model Backbone=Llama 3...
2026.05
0.301
MEMPR
Model Backbone=Llama 3 8B
2026.05
0.077
COMPACTOR
Model Backbone=Llama 3 8B
2026.05
0.028
MEMPR
Model Backbone=Claude...
2026.05
0.016
HUMPR
Model Backbone=Claude...
2026.05
0.015
COMPACTOR
Model Backbone=Claude...
2026.05
-0.013
HUMPR
Model Backbone=Llama 3 8B
2026.05
-0.072
Feedback
Search any
task
Search any
task