Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Tool-use instruction following on ToolBench I3-Instruction
Loading...
71
Pass Rate
DFSDT
-2.84
16.33
35.5
54.67
Jul 31, 2023
Pass Rate
Win Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass Rate
Win Rate
DFSDT
Backbone=GPT-4, Retrie...
2023.07
71
84
DFSDT
Backbone=ToolLLaMA, Re...
2023.07
66
69
DFSDT
Backbone=ToolLLaMA, Re...
2023.07
65
73
DFSDT
Backbone=ChatGPT, Retr...
2023.07
62
69
ReACT
Backbone=GPT-4, Retrie...
2023.07
47
78
DFSDT
Backbone=Text-Davinci-...
2023.07
46
63
DFSDT
Backbone=Claude-2, Ret...
2023.07
28
65
ReACT
Backbone=ToolLLaMA, Re...
2023.07
25
55
ReACT
Backbone=Text-Davinci-...
2023.07
24
45
ReACT
Backbone=ChatGPT, Retr...
2023.07
22
-
ReACT
Backbone=Claude-2, Ret...
2023.07
14
47.5
ReACT & DFSDT
Backbone=Vicuna, Retri...
2023.07
0
0
ReACT & DFSDT
Backbone=Alpaca, Retri...
2023.07
0
0
Feedback
Search any
task
Search any
task