A Careful Examination of Large Language Model Performance on Grade School Arithmetic · HackerPapers discussions

A Careful Examination of Large Language Model Performance on Grade School Arithmetic — mentioned by kalkin

Tue, 02 Dec 2025 16:59:49 GMT

Scale AI wrote a paper a year ago comparing various models performance on benchmarks to performance on similar but held-out questions. Generally the closed source models performed better, and Mistral came out looking pretty badly: https://arxiv.org/pdf/2405.00332

Paper and discussion history. A mention is not an endorsement.

A Careful Examination of Large Language Model Performance on Grade School Arithmetic — HN submission

Sun, 05 May 2024 19:11:50 GMT

A Careful Examination of LLM Performance on Grade School Arithmetic

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

A Careful Examination of Large Language Model Performance on Grade School Arithmetic — HN submission

Fri, 03 May 2024 06:13:25 GMT

Examination of Large Language Model Performance on Grade School Arithmetic

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

A Careful Examination of Large Language Model Performance on Grade School Arithmetic — HN submission

Thu, 02 May 2024 20:59:28 GMT

An Examination of Large Language Model Performance on Grade School Arithmetic

8 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

A Careful Examination of Large Language Model Performance on Grade School Arithmetic — HN submission

Thu, 02 May 2024 06:44:52 GMT

A Careful Examination of LLM Performance on Grade School Arithmetic

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.