SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? Paper • 2608.19799 • Published 11 days ago • 65
PolyReal: A Benchmark for Real-World Polymer Science Workflows Paper • 2604.02934 • Published Apr 3 • 1
Runtime error Agents 3 SpectrumLeaderboard 🚀 3 Explore and filter the Spectral Analysis Model Leaderboard