{"slug": "long-horizon-terminal-bench", "title": "Long-Horizon Terminal-Bench", "summary": "A new benchmark, Long-Horizon Terminal-Bench, evaluates AI agents on 46 terminal tasks across nine categories, including software engineering and scientific computing, using a 90-minute budget and hidden replay-based verifiers. Grok 4.5 achieved the top score of 0.51, highlighting challenges in long-horizon planning and iterative debugging.", "body_md": "Long-Horizon Terminal-Bench evaluates whether agents can sustain progress on 46 reproducible terminal tasks spanning nine categories, including software engineering, scientific computing, multimodal analysis, research reproduction, systems, professional workflows, games, and logic puzzles. Tasks run in containers under a 90-minute budget and use hidden replay-based verifiers with continuous partial credit, stressing long-horizon planning, context management, iterative debugging, and recovery across hundreds of dependent actions. Category: Agentic. Imported rows: 21. Top imported result: Grok 4.5, rank 1, 0.51.", "url": "https://wpnews.pro/news/long-horizon-terminal-bench", "canonical_source": "https://benchmarklist.com/benchmarks/long_horizon_terminal_bench/", "published_at": "2026-07-09 00:00:00+00:00", "updated_at": "2026-07-16 21:56:14.698548+00:00", "lang": "en", "topics": ["ai-agents", "ai-research", "ai-tools", "artificial-intelligence"], "entities": ["Grok 4.5"], "alternates": {"html": "https://wpnews.pro/news/long-horizon-terminal-bench", "markdown": "https://wpnews.pro/news/long-horizon-terminal-bench.md", "text": "https://wpnews.pro/news/long-horizon-terminal-bench.txt", "jsonld": "https://wpnews.pro/news/long-horizon-terminal-bench.jsonld"}}