SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence Paper • 2512.22334 • Published about 1 month ago • 35
SGI-Bench Collection Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows • 9 items • Updated Dec 24, 2025 • 30
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows Paper • 2512.16969 • Published Dec 18, 2025 • 117
JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence Paper • 2510.23538 • Published Oct 27, 2025 • 97