Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task-Efficient Routing on Science Curated Task Benchmark 1.0 (test)
Loading...
0.0054
Average Cost
Force Weak
0.00026
0.034955
0.06965
0.104345
Jan 27, 2026
Average Cost
Reduction
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Cost
Reduction
Average Score
Force Weak
Strategy=Force Weak
2026.01
0.0054
96
90.2
CASTER
Strategy=CASTER
2026.01
0.0831
37.9
95.3
Force Strong
Strategy=Force Strong
2026.01
0.1339
-
95.2
Feedback
Search any
task
Search any
task