Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Aggregate Cognitive Performance on Average
Loading...
76.6
Human-Model Similarity (1-nWD)
TASKPR
-3.064
17.618
38.3
58.982
May 25, 2026
Human-Model Similarity (1-nWD)
Updated 8d ago
Evaluation Results
Method
Method
Links
Human-Model Similarity (1-nWD)
TASKPR
Model Backbone=Llama 3 8B
2026.05
76.6
TASKPR
Model Backbone=Claude...
2026.05
60.3
COMPACTOR
Model Backbone=Claude...
2026.05
6.9
COMPACTOR
Model Backbone=Llama 3 8B
2026.05
5.4
MEMPR
Model Backbone=Llama 3 8B
2026.05
1.6
HUMPR
Model Backbone=Llama 3 8B
2026.05
1
HUMPR
Model Backbone=Claude...
2026.05
0.4
MEMPR
Model Backbone=Claude...
2026.05
0
Feedback
Search any
task
Search any
task