<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>devtake.dev — #swe-bench</title><description>Articles tagged swe-bench on devtake.dev.</description><link>https://devtake.dev/</link><language>en-us</language><item><title>OpenAI just retired SWE-bench Verified. The headline coding benchmark of 2025 is officially saturated.</title><link>https://devtake.dev/article/openai-retires-swe-bench-verified/</link><guid isPermaLink="true">https://devtake.dev/article/openai-retires-swe-bench-verified/</guid><description>OpenAI says SWE-bench Verified is saturated and contaminated, and 60% of remaining problems are unsolvable. Here&apos;s what comes next, and why every coding leaderboard is suspect.</description><pubDate>Mon, 27 Apr 2026 10:00:00 GMT</pubDate><category>ai</category><category>openai</category><category>swe-bench</category><category>benchmarks</category><category>ai-models</category><category>llm</category><category>ai-coding</category><category>evaluations</category><category>claude-opus</category><author>dieter-morelli</author></item></channel></rss>