Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.22340 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909370808270848 |
|---|---|
| author | Davis, Ernest |
| author_facet | Davis, Ernest |
| contents | In August 2023, Scott Aaronson and I reported the results of testing GPT4 with the Wolfram Alpha and Code Interpreter plug-ins over a collection of 105 original high-school level and college-level science and math problems (Davis and Aaronson, 2023). In September 2024, I tested the recently released model GPT-4o1-preview on the same collection. Overall I found that performance had significantly improved, but was still considerably short of perfect. In particular, problems that involve spatial reasoning are often stumbling blocks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22340 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Testing GPT-4-o1-preview on math and science problems: A follow-up study Davis, Ernest Computers and Society Artificial Intelligence In August 2023, Scott Aaronson and I reported the results of testing GPT4 with the Wolfram Alpha and Code Interpreter plug-ins over a collection of 105 original high-school level and college-level science and math problems (Davis and Aaronson, 2023). In September 2024, I tested the recently released model GPT-4o1-preview on the same collection. Overall I found that performance had significantly improved, but was still considerably short of perfect. In particular, problems that involve spatial reasoning are often stumbling blocks. |
| title | Testing GPT-4-o1-preview on math and science problems: A follow-up study |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2410.22340 |