Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs Paper • 2605.09063 • Published 28 days ago • 80
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity Paper • 2605.05662 • Published 30 days ago • 11
Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level Math Paper • 2602.06291 • Published Feb 6 • 24
Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought Paper • 2510.04230 • Published Oct 5, 2025 • 27