{"slug": "genebench-pro", "title": "GeneBench-Pro", "summary": "Researchers released GeneBench-Pro, a 129-problem benchmark testing AI agents on multi-stage genomics and biomedicine analyses. GPT-5.6 Sol Pro (Extended) achieved the top score of 31.5%, highlighting the difficulty of realistic scientific workflows for current AI systems.", "body_md": "GeneBench-Pro is a 129-problem benchmark for AI agents performing realistic multi-stage scientific analyses in genomics, quantitative biology, and translational biomedicine. Problems require agents to inspect messy datasets, choose and revise analysis workflows, and return decision-relevant quantitative answers under ambiguity. Category: Biology. Imported rows: 29. Top imported result: GPT-5.6 Sol Pro (Extended), rank 1, 31.5%.", "url": "https://wpnews.pro/news/genebench-pro", "canonical_source": "https://benchmarklist.com/benchmarks/genebench_pro/", "published_at": "2026-06-30 00:00:00+00:00", "updated_at": "2026-07-15 19:00:17.380587+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research"], "entities": ["GeneBench-Pro", "GPT-5.6 Sol Pro (Extended)"], "alternates": {"html": "https://wpnews.pro/news/genebench-pro", "markdown": "https://wpnews.pro/news/genebench-pro.md", "text": "https://wpnews.pro/news/genebench-pro.txt", "jsonld": "https://wpnews.pro/news/genebench-pro.jsonld"}}