Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Tool-use Planning on ToolBench G2-Instruction
Loading...
87.59
Win Rate
GPT4 TOPGUN
49.3284
59.2617
69.195
79.1283
Feb 15, 2024
Win Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Win Rate
GPT4 TOPGUN
Reference=ChatGPT REACT
2024.02
87.59
GPT4 TOPGUN
Reference=T.LLAMA REACT
2024.02
86.24
GPT4 TOPGUN
Reference=T.LLAMA DFSD...
2024.02
83.07
GPT4 TOPGUN
Reference=ChatGPT DFSDT
2024.02
81.63
GPT4 TOPGUN
Reference=GPT4 ReACT
2024.02
78.61
GPT4 TOPGUN
Reference=T.LLAMA DFSDT
2024.02
78.31
GPT4 TOPGUN
Reference=GPT4 DFSDT
2024.02
73.92
GPT4 DFSDT
Reference=ChatGPT REACT
2024.02
73.3
ChatGPT DFSDT
Reference=ChatGPT REACT
2024.02
72
T.LLAMA DFSDT
Reference=ChatGPT REACT
2024.02
68.5
T.LLAMA DFSDT+Ret
Reference=ChatGPT REACT
2024.02
68.5
GPT4 ReACT
Reference=ChatGPT REACT
2024.02
65.8
T.LLAMA REACT
Reference=ChatGPT REACT
2024.02
50.8
Feedback
Search any
task
Search any
task