Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Single-agent tool selection on GTA
Loading...
100
Top-1 Acc
LLM Direct
97.0152
97.7901
98.565
99.3399
Jan 29, 2026
Top-1 Acc
Updated 1mo ago
Evaluation Results
Method
Method
Links
Top-1 Acc
LLM Direct
Retrieval/Ranking Stra...
2026.01
100
SARL
Retrieval/Ranking Stra...
2026.01
100
Cos-sim Direct
Retrieval/Ranking Stra...
2026.01
97.2
Cos-sim+Rank
Retrieval/Ranking Stra...
2026.01
97.13
Feedback
Search any
task
Search any
task