Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Symbolic Reasoning (Equations) on NoRa Inaccurate Rationales
Loading...
53.3
Accuracy
CD-CoT
7.332
19.266
31.2
43.134
Oct 31, 2024
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
CD-CoT
Model=Gemini-Pro
2024.10
53.3
SC
Model=Gemini-Pro
2024.10
45
CD-CoT
Model=GPT-3.5-turbo
2024.10
41.3
Base
Model=Gemini-Pro
2024.10
36.7
CC
Model=Gemini-Pro
2024.10
35
CC
Model=GPT-3.5-turbo
2024.10
33
SC
Model=GPT-3.5-turbo
2024.10
30.7
BT
Model=Gemini-Pro
2024.10
28.7
Base
Model=GPT-3.5-turbo
2024.10
26.1
BT
Model=GPT-3.5-turbo
2024.10
22.7
CD-CoT
Model=Mixtral 8x7B
2024.10
21.3
CC
Model=Mixtral 8x7B
2024.10
18.3
SC
Model=Mixtral 8x7B
2024.10
18
Base
Model=Mixtral 8x7B
2024.10
15.1
CC
Model=LLaMA2-70B
2024.10
14
BT
Model=LLaMA2-70B
2024.10
12.5
BT
Model=Mixtral 8x7B
2024.10
10.1
SC
Model=LLaMA2-70B
2024.10
9.7
CD-CoT
Model=LLaMA2-70B
2024.10
9.7
Base
Model=LLaMA2-70B
2024.10
9.1
Feedback
Search any
task
Search any
task
