Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent Performance and Efficiency on DunCrew
Loading...
96.4
Success Rate
Triggered
86.416
89.008
91.6
94.192
Apr 5, 2026
Success Rate
Average Tokens Used
Average Interaction Length
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Average Tokens Used
Average Interaction Length
Triggered
Sample size (N)=193
2026.04
96.4
179
16.3
Post-Governor (all)
Sample size (N)=246
2026.04
94.3
154
14
Pre-Governor
Sample size (N)=101
2026.04
88.1
275
22.2
Not triggered
Sample size (N)=53
2026.04
86.8
65
5.6
Feedback
Search any
task
Search any
task