Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Agentic Search on Agentic-Wide TaskCraft (test)
Loading...
90.1
Accuracy
A-MAPREDUCE
73.6264
77.9032
82.18
86.4568
Feb 1, 2026
Accuracy
Delay (s)
Cost ($)
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Delay (s)
Cost ($)
A-MAPREDUCE
Backbone=GPT-5-mini
2026.02
90.1
384.07
0.09
Flash-Searcher
Backbone=GPT-5-mini
2026.02
87.13
275.9
0.06
SmolAgents
Backbone=GPT-5-mini
2026.02
80.2
607.04
0.12
OWL
Backbone=GPT-5-mini
2026.02
74.26
702.48
0.08
Feedback
Search any
task
Search any
task