{"type":"analysis","id":"analysis:choosing-which-tasks-go-to-agents-may-save-more-than-openai-s-new-discounts-but","slug":"choosing-which-tasks-go-to-agents-may-save-more-than-openai-s-new-discounts-but","title":"Choosing which tasks go to agents may save more than OpenAI's new discounts, but only if failed runs cost as much as successful ones","description":"OpenAI's report puts agent success at 79% on one research task and 25% on another. If failed runs cost about as much as successful ones, that spread moves the cost per finished task more than a 40% token discount does. OpenAI has not published spend by task type, so teams have to measure it themselves.","published_at":"2026-11-19T15:00:00.000Z","updated_at":"2026-11-19T15:00:00.000Z","record_date":"2026-11-19","topics":["openai","agents","research"],"source_urls":["https://openai.com/index/research-acceleration-jagged-frontier","https://openai.com/index/introducing-gpt-6-2-astra-sol","https://deploymentsafety.openai.com/gpt-6-cyber","https://x.com/OpenAIDevs/status/2123188195202617408","https://t.me/qwgai/4338"],"language":"en","routes":{"html":"https://newruntime.com/analysis/choosing-which-tasks-go-to-agents-may-save-more-than-openai-s-new-discounts-but/","markdown":"https://newruntime.com/analysis/choosing-which-tasks-go-to-agents-may-save-more-than-openai-s-new-discounts-but.md","json":"https://newruntime.com/analysis/choosing-which-tasks-go-to-agents-may-save-more-than-openai-s-new-discounts-but.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":"story_cluster:openai-research-on-coding-agents-uneven-acceleration-of-ai-research-4a5d4b8dae39","authorial_article_id":"f88a8e12-5cb5-41eb-a340-7ba2495d0e90"},"markdown_url":"https://newruntime.com/analysis/choosing-which-tasks-go-to-agents-may-save-more-than-openai-s-new-discounts-but.md","retrieval_nugget":"OpenAI's report puts agent success at 79% on one research task and 25% on another. If failed runs cost about as much as successful ones, that spread moves the cost per finished task more than a 40% token discount does.","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":"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":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}
