Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-turn Interaction-based Problem Solving on MINT-Bench 1.0 (test)
Loading...
11.76
Code Generation Score
LLAMA PRO - INSTRUCT
-0.4704
2.7048
5.88
9.0552
Jan 4, 2024
Code Generation Score
Decision Making Score
Reasoning Score
Micro Average Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Code Generation Score
Decision Making Score
Reasoning Score
Micro Average Score
LLAMA PRO - INSTRUCT
interaction turns (k)=5
2024.01
11.76
29.1
9.81
14.68
Mistral-Instruct-v0.1
interaction turns (k)=5
2024.01
6.62
34.33
8.54
13.99
CodeLLaMA-7B-Instruct
interaction turns (k)=5
2024.01
2.21
17.16
7.91
8.7
AgentLM-7B
interaction turns (k)=5
2024.01
1.47
9.7
8.86
7.34
LLaMA2-7B-Chat
interaction turns (k)=5
2024.01
0
0
13.61
7.34
Feedback
Search any
task
Search any
task