Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Purpose Tool Use on NESTFUL
Loading...
96.3
F1 Functional
No Memory
93.076
93.913
94.75
95.587
Jun 6, 2026
F1 Functional
F1 Parameter
Partial Accuracy
Full Accuracy
Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Functional
F1 Parameter
Partial Accuracy
Full Accuracy
Win Rate
No Memory
Backbone=Claude 3.7 So...
2026.06
96.3
61.3
31.9
15.6
51.2
MemToolAgent
Backbone=Claude 3.7 So...
2026.06
96
78
40.6
30.4
70.2
Extended Thinking
Backbone=Claude 3.7 So...
2026.06
95.2
62.7
33.4
16.9
66.1
ReAct Agent
Backbone=Claude 3.7 So...
2026.06
93.2
56.4
29.5
10.8
58.2
Feedback
Search any
task
Search any
task