Home/ tech TECHOpenAI: SWE-bench Verified no longer measures frontier coding capabilitiesOpenAI announces SWE-bench Verified no longer adequately reflects performance of next-generation coding models.Published 12sem·1 sourceNotable Lire en françaisListen≈ 13sSpeed0.8×1×1.2×1.5×The factBenchmark becomes insufficient to measure recent advances in automated coding.🔗Click the link to read an article on the topic:Hacker News (YC)↗🧭Explore this topicOpenAI#openai#benchmark#codage#iaWhat if you saw the whole news differently?Factae cross-checks hundreds of sources worldwide to keep only the fact, no opinion. Explore the front page.→Follow topic →↗ Share the newsAuto-synthesis from 1 media source · identified on April 26, 2026← Back to home