Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Adaptive Tool Use on MetaTool
Loading...
520
Tool Invocations Count
Always Call
193.44
278.22
363
447.78
Feb 18, 2025
Tool Invocations Count
Decision Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Tool Invocations Count
Decision Accuracy
Always Call
Backbone=LM3-8B, Fine-...
2025.02
520
0.5
Always Call
Backbone=LM3-8B, Fine-...
2025.02
520
0.5
Naive
Backbone=LM3-8B, Fine-...
2025.02
296
0.619
Naive
Backbone=LM3-8B, Fine-...
2025.02
277
0.821
Pyes
Backbone=LM3-8B, Fine-...
2025.02
273
0.817
MeCo
Backbone=LM3-8B, Fine-...
2025.02
240
0.843
Pyes
Backbone=LM3-8B, Fine-...
2025.02
208
0.635
MeCo
Backbone=LM3-8B, Fine-...
2025.02
206
0.65
Feedback
Search any
task
Search any
task