Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Tool-augmented reasoning on MINT-Bench
Loading...
9.85
Success Rate (Turn 1)
LLAMA PRO - INSTRUCT
-0.394
2.2655
4.925
7.5845
Jan 4, 2024
Success Rate (Turn 1)
Success Rate (Turn 2)
Success Rate (Turn 3)
Success Rate (Turn 4)
Success Rate (Turn 5)
Average Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate (Turn 1)
Success Rate (Turn 2)
Success Rate (Turn 3)
Success Rate (Turn 4)
Success Rate (Turn 5)
Average Success Rate
LLAMA PRO - INSTRUCT
2024.01
9.85
12.65
12.8
11.95
14.68
12.38
Mistral-Instruct-v0.1
2024.01
1.54
12.12
13.31
14.16
13.99
11.02
LLaMA2-7B-Chat
2024.01
1.02
4.27
9.77
6.48
7.34
5.77
CodeLLaMA-7B-Instruct
2024.01
0.34
7.85
10.24
9.73
8.7
7.37
AgentLM-7B
2024.01
0
4.44
5.29
6.48
7.34
4.71
Feedback
Search any
task
Search any
task