#评估标准

2 stories · 0 in 7 days · 0 in 30 days

Stories, products and papers tagged "评估标准", newest first.

Sep 16

SWE-bench audit shows coding agents can't be ranked

This matters to developers because it shows that the current leaderboard doesn't provide a reliable way to compare coding agents, which could lead to misinformed decisions about which tool to use.

#SWE-bench #coding agents #leaderboard #benchmark

arXiv cs.AI@Fengshuo Liu et al. (5)Source

Jun 11

PapersSelected72°08:53

Chinese contentAgents' Last Exam 揭示：前沿智能体在真实工作中远未达标

这篇论文戳破了AI基准测试的泡沫——高分不等于能干实事。做AI自动化部署的团队、评估智能体能力的开发者，看完会重新审视自己的测试标准，建议点开看看真实工作场景的差距。

#智能体 #基准测试 #真实工作 #自动化

rohanpaul_ai@rohanpaul_aiSource