Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent Retrieval on ToolE
Loading...
74.27
nDCG
AutoMAS (Retriever + re-ranker)
51.6812
57.5456
63.41
69.2744
May 5, 2026
nDCG
Recall
mAP
Updated 28d ago
Evaluation Results
Method
Method
Links
nDCG
Recall
mAP
AutoMAS (Retriever + re-ranker)
Re-Ranker=gpt4o, k=5,...
2026.05
74.27
80.58
79.19
AutoMAS (Retriever + re-ranker)
Re-Ranker=gpt4o, k=5,...
2026.05
74.27
83.46
81.08
AutoMAS (Retriever + re-ranker)
Re-Ranker=gpt4o, k=10,...
2026.05
74.16
81.22
79.63
AutoMAS (Retriever + re-ranker)
Re-Ranker=gpt4o, k=10,...
2026.05
74.16
83.98
81.73
Re-Invoke w/ Vertex AI
Re-Ranker=text-bison@001
2026.05
67.16
78.21
67.15
Re-Invoke w/ BM25
Re-Ranker=gpt-3.5 turbo
2026.05
52.55
63
52.55
Feedback
Search any
task
Search any
task