一句话摘要
V2.5 末期的小版本迭代,数学和编程 benchmark 小幅提升,改进文件处理和摘要功能。
详细描述
deepseek-chat upgraded to DeepSeek-V2.5-1210. MATH-500 improved from 74.8% to 82.8%, LiveCodeBench (08.01-12.01) from 29.2% to 34.38%. Optimized file upload and webpage summarization.
deepseek-chat 升级至 V2.5-1210,MATH-500 提升至 82.8%,LiveCodeBench 提升至 34.38%,优化文件上传和网页摘要功能。
原文摘录
MATH-500 benchmark has improved from 74.8% to 82.8%. Coding: Accuracy on the LiveCodebench (08.01 - 12.01) benchmark has increased from 29.2% to 34.38%. Optimized the user experience for file upload and webpage summarization functionalities.