DNA 3.0 Collection DNA 3.0 preserves Qwen 3.5/3.6 strengths while removing censorship on China-related topics. • 8 items • Updated 4 days ago • 4
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs Paper • 2605.09063 • Published 24 days ago • 80
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs Paper • 2605.09063 • Published 24 days ago • 80