From Conversation to Evaluation: Benchmarking LLMs on Development Knowledge via SimpleDevQA

arXiv:2512.08867 · cs.SE · Submitted 2025-12-09 · Read on arXiv

cs.SE

Submitted: 2025-12-09

Updated: 2026-11-13

DOI: 10.18653/v1/2026.findings-acl.1877

Code: https://github.com/openai/tiktoken

Project page: https://evalplus.github.io/leaderboard.html

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Sources

Related papers