{"type":"analysis","id":"analysis:research-artificial-analysis-zeros-reward-hacked-coding-agent-passes-with-two-detectors","slug":"research-artificial-analysis-zeros-reward-hacked-coding-agent-passes-with-two-detectors","title":"Artificial Analysis zeros reward-hacked coding-agent passes with two detectors","description":"The Coding Agent Index now treats reward hacking as a scored failure. FrontierCode uses a modified Cognition scanner; Terminal-Bench uses an LLM trajectory judge. Public per-agent rates remain marked coming soon.","published_at":"2026-10-25T08:00:00.000Z","updated_at":"2026-10-25T08:00:00.000Z","record_date":"2026-10-25","topics":["agents","claude","cursor","research"],"source_urls":["https://artificialanalysis.ai/methodology/coding-agents-benchmarking","https://cognition.com/blog/frontier-code-1.1","https://cognition.com/frontiercode","https://artificialanalysis.ai/evaluations/frontiercode","https://artificialanalysis.ai/articles/frontiercode","https://www.tbench.ai/news/leaderboard-integrity-update","https://artificialanalysis.ai/evaluations/terminalbench-4-0","https://huggingface.co/datasets/ArtificialAnalysis/SWE-Atlas-QnA-AA","https://github.com/harbor-framework/terminal-bench/issues/2086","https://www.tbench.ai/news/terminal-bench-4-0","https://samaritan-research.org/benchmarks/terminal-bench-4/review","https://github.com/harbor-framework/harbor/issues/3725","https://cursor.com/blog/reward-hacking-coding-benchmarks","https://artificialanalysis.ai/agents/coding-agents","https://coding-index.posttrain.dev"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-artificial-analysis-zeros-reward-hacked-coding-agent-passes-with-two-detectors/","markdown":"https://newruntime.com/analysis/research-artificial-analysis-zeros-reward-hacked-coding-agent-passes-with-two-detectors.md","json":"https://newruntime.com/analysis/research-artificial-analysis-zeros-reward-hacked-coding-agent-passes-with-two-detectors.json"},"author":{"role":"author","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:3e1dd184-2a75-43e8-8aa3-7fd01c84ab2e","authorial_article_id":"3e1dd184-2a75-43e8-8aa3-7fd01c84ab2e"},"next_reads":[{"type":"topic","path":"/topics/agents/","url":"https://newruntime.com/topics/agents/","title":"Agents","reason":"Explore the agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agents.md","json_url":"https://newruntime.com/topics/agents.json"},{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.json"},{"type":"topic","path":"/topics/cursor/","url":"https://newruntime.com/topics/cursor/","title":"Cursor","reason":"Explore the cursor topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/cursor.md","json_url":"https://newruntime.com/topics/cursor.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}