{"type":"analysis","id":"analysis:research-decepticon-s-102-104-xbow-score-is-self-reported-ran-with-hints-and-uses-a","slug":"research-decepticon-s-102-104-xbow-score-is-self-reported-ran-with-hints-and-uses-a","title":"Decepticon's 102/104 XBOW score is self-reported, ran with hints, and uses a benchmark its creators now call saturated","description":"PurpleAILAB's agent publishes per-tier results and run traces, but not the model it used or what its \"cycles\" mean, and no one has reproduced the run. XBOW itself says top systems now score about 100% on these benchmarks.","published_at":"2026-10-22T01:00:00.000Z","updated_at":"2026-10-22T01:00:00.000Z","record_date":"2026-10-22","topics":["benchmarks","agents","research"],"source_urls":["https://github.com/PurpleAILAB/Decepticon/blob/main/benchmark/results/README.md","https://github.com/PurpleAILAB/xbow-validation-benchmarks","https://github.com/PurpleAILAB/Decepticon/tree/main/benchmark","https://github.com/PurpleAILAB/Decepticon/blob/main/benchmark/README.md","https://github.com/PurpleAILAB/Decepticon","https://github.com/PurpleAILAB/Decepticon/blob/main/docs/benchmark-comparison.md","https://github.com/KeygraphHQ/xbow-validation-benchmarks","https://github.com/xbow-engineering/validation-benchmarks"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-decepticon-s-102-104-xbow-score-is-self-reported-ran-with-hints-and-uses-a/","markdown":"https://newruntime.com/analysis/research-decepticon-s-102-104-xbow-score-is-self-reported-ran-with-hints-and-uses-a.md","json":"https://newruntime.com/analysis/research-decepticon-s-102-104-xbow-score-is-self-reported-ran-with-hints-and-uses-a.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:86a42f3e-4ede-4490-a258-58be8923eb68","authorial_article_id":"86a42f3e-4ede-4490-a258-58be8923eb68"},"next_reads":[{"type":"topic","path":"/topics/benchmarks/","url":"https://newruntime.com/topics/benchmarks/","title":"Benchmarks","reason":"Explore the benchmarks topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/benchmarks.md","json_url":"https://newruntime.com/topics/benchmarks.json"},{"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/research/","url":"https://newruntime.com/topics/research/","title":"Research","reason":"Explore the research topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/research.md","json_url":"https://newruntime.com/topics/research.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"}]}