Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Symbolic Reasoning on Date
Loading...
90.5
Solve Rate
Automatic Model Selection with LLMs
24.252
41.451
58.65
75.849
Nov 18, 2022
Dec 19, 2022
Jan 19, 2023
Feb 19, 2023
Mar 22, 2023
Apr 22, 2023
May 23, 2023
Solve Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Solve Rate
Automatic Model Selection with LLMs
Backbone=GPT-4, Decodi...
2023.05
90.5
CoT
Backbone=GPT-4, Decodi...
2023.05
90
PAL
Backbone=GPT-4, Decodi...
2023.05
88.1
Automatic Model Selection with LLMs
Backbone=Codex, Decodi...
2023.05
79.4
PAL
Backbone=Codex, Decodi...
2023.05
77.5
PAL Codex
Prompting Strategy=Pro...
2022.11
76.2
Automatic Model Selection with LLMs
Backbone=ChatGPT, Deco...
2023.05
70.2
CoT
Backbone=ChatGPT, Deco...
2023.05
69.1
PAL
Backbone=ChatGPT, Deco...
2023.05
68.3
COT PaLM-540B
Prompting Strategy=Cha...
2022.11
65.3
CoT
Backbone=Codex, Decodi...
2023.05
64.5
COT Codex
Prompting Strategy=Cha...
2022.11
61.8
DIRECT Codex
Prompting Strategy=Dir...
2022.11
49.9
COT LaMDA-137B
Prompting Strategy=Cha...
2022.11
26.8
Feedback
Search any
task
Search any
task