Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Arithmetic Reasoning on AddSub (test)
Loading...
96.71
Accuracy
CoT + Skill-Based
88.0156
90.2728
92.53
94.7872
Jun 6, 2023
Aug 3, 2023
Sep 30, 2023
Nov 27, 2023
Jan 24, 2024
Mar 22, 2024
May 20, 2024
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
CoT + Skill-Based
Prompting=Chain-of-Tho...
2024.05
96.71
CoT + PAL
Prompting=Hybrid CoT +...
2024.05
95.7
PAL
Prompting=Program-Aide...
2024.05
94.9
CoT
Prompting=Chain-of-Tho...
2024.05
93.9
Ours (Natural Program (NP), No Verification)
LLM=GPT-3.5-turbo, Pro...
2023.06
93.67
Ours (NP + Deductive Verification + UPV)
LLM=GPT-3.5-turbo, Pro...
2023.06
93.54
CoT + Voting
LLM=GPT-3.5-turbo, Pro...
2023.06
92.36
Faithful CoT + Voting
LLM=GPT-3.5-turbo, Pro...
2023.06
88.35
Feedback
Search any
task
Search any
task