https://paperswithcode.com/sota/arith...
https://arxiv.org/pdf/2404.14963v3.pdf
https://arxiv.org/pdf/2308.07921v1.pdf

0:00 Introduction to GSM 8K Benchmark
0:47 Flattening of Scores in Recent Years
1:20 Top Approach: "Deeply Understanding the Problem"
1:45 Three-Step Problem-Solving Method
3:08 Comparison to Zero-Shot Chain of Thought
3:39 Second Top Approach: Code Generation
4:15 Code Interpreter and GPT-4
5:24 Variations in Code-Based Problem Solving
6:17 Majority Voting to Increase Accuracy
6:34 Final Results and Comparison
7:16 Implications and Future Challenges
8:02 Conclusion and Call to Action