<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>SWE-Bench on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/swe-bench/</link><description>Recent content in SWE-Bench on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Tue, 30 Jun 2026 16:10:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/swe-bench/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Agent 评测基准 2026：GAIA、SWE-bench、AgentBench 横评</title><link>https://guijiagi.com/posts/agent-evaluation-benchmarks-2026/</link><pubDate>Tue, 30 Jun 2026 16:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-evaluation-benchmarks-2026/</guid><description>2026年主流Agent评测基准深度解析：GAIA、SWE-bench、AgentBench、WebArena等评测体系的能力维度与局限性</description></item><item><title>代码大模型2026排行：SWE-Bench Pro时代</title><link>https://guijiagi.com/posts/code-llm-2026-ranking/</link><pubDate>Tue, 30 Jun 2026 11:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/code-llm-2026-ranking/</guid><description>2026年代码大模型排行榜，以SWE-Bench Pro为核心基准的全面对比</description></item><item><title>代码大模型 2026 排行：SWE-Bench Pro 时代的编程能力</title><link>https://guijiagi.com/posts/code-llm-2026-ranking-swebench-pro-era/</link><pubDate>Sun, 28 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/code-llm-2026-ranking-swebench-pro-era/</guid><description>2026年代码大模型全面排行，以SWE-Bench Pro为核心的编程能力深度评测</description></item><item><title>代码 LLM 评估：从 HumanEval 到 SWE-Bench Pro</title><link>https://guijiagi.com/posts/code-llm-eval/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/code-llm-eval/</guid><description>代码 LLM 评估全景：从基础 HumanEval/MBPP 到工程级 SWE-Bench Pro</description></item></channel></rss>