Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Implicit-need coverage evaluation on implicit-intent Scene A: cafe v2
Loading...
80
Implicit-Need Coverage
AURA Intent
17.6
33.8
50
66.2
Jun 4, 2026
Implicit-Need Coverage
Intent–NoIntent Δ
p-value
Updated 1mo ago
Evaluation Results
Method
Method
Links
Implicit-Need Coverage
Intent–NoIntent Δ
p-value
AURA Intent
Backbone=gpt-4o-mini,...
2026.06
80
0.091
0.004
NoIntent
Backbone=gpt-4o-mini,...
2026.06
70.9
-
-
Literal
Backbone=gpt-4o-mini,...
2026.06
20
-
-
Feedback
Search any
task
Search any
task