Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool Retrieval on GeoPlan-bench Complex
Loading...
69.7
Recall@k
BSCTR
9.5776
25.1863
40.795
56.4037
Apr 29, 2026
Recall@k
NDCG@k
F1-Score
Call Recall
Similarity (LCS)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Recall@k
NDCG@k
F1-Score
Call Recall
Similarity (LCS)
BSCTR
2026.04
69.7
66.66
67.9
58.26
32.05
Query Rewriting
2026.04
67.13
62.23
64.35
54.38
29.48
Graph-based
2026.04
48.28
54.08
50.54
20.14
14.96
Dense
2026.04
18.3
30.73
24.52
15.23
11.19
BM25
2026.04
11.89
15.79
13.42
9.45
8.25
Feedback
Search any
task
Search any
task