Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Proactive Assistance on ProActEval 200 scenarios
Loading...
5.6
T80 Score
ProactiveAgent
5.5272
5.5461
5.565
5.5839
May 25, 2026
T80 Score
T100 Score
User Effort
Judge-labeled Anticipation Rate
Anticipated Needs Count
Updated 8d ago
Evaluation Results
Method
Method
Links
T80 Score
T100 Score
User Effort
Judge-labeled Anticipation Rate
Anticipated Needs Count
ProactiveAgent
Prompting Baseline=GPT-4o
2026.05
5.6
7.145
8.425
2
32
ProAct
Configuration=Directed...
2026.05
5.53
6.91
8.075
44.7
703
Feedback
Search any
task
Search any
task