{"type":"analysis","id":"analysis:research-cheaper-reasoning-models-often-cost-more-per-task-but-the-reversal-numbers","slug":"research-cheaper-reasoning-models-often-cost-more-per-task-but-the-reversal-numbers","title":"Cheaper reasoning models often cost more per task, but the reversal numbers depend on a single study","description":"A Stanford/Berkeley-affiliated study found that the model with the lower list price cost more in about a third of model-pair comparisons. Independent work points the same way, because thinking tokens dominate spend. Price reversal itself has been measured in only one study, though, and that study ignores answer quality.","published_at":"2026-10-22T22:00:00.000Z","updated_at":"2026-10-22T22:00:00.000Z","record_date":"2026-10-22","topics":["reasoning","gemini","claude","research"],"source_urls":["https://arxiv.org/abs/2603.23971","https://arxiv.org/html/2603.23971v2","https://arxiv.org/html/2603.23971v1","https://nousresearch.com/measuring-thinking-efficiency-in-reasoning-models-the-missing-benchmark/","https://arxiv.org/abs/2608.26235","https://arxiv.org/abs/2608.16956"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-cheaper-reasoning-models-often-cost-more-per-task-but-the-reversal-numbers/","markdown":"https://newruntime.com/analysis/research-cheaper-reasoning-models-often-cost-more-per-task-but-the-reversal-numbers.md","json":"https://newruntime.com/analysis/research-cheaper-reasoning-models-often-cost-more-per-task-but-the-reversal-numbers.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:f64886fe-d8fb-4fe4-b44e-9b3d971af557","authorial_article_id":"f64886fe-d8fb-4fe4-b44e-9b3d971af557"},"next_reads":[{"type":"topic","path":"/topics/reasoning/","url":"https://newruntime.com/topics/reasoning/","title":"Reasoning","reason":"Explore the reasoning topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/reasoning.md","json_url":"https://newruntime.com/topics/reasoning.json"},{"type":"topic","path":"/topics/gemini/","url":"https://newruntime.com/topics/gemini/","title":"Gemini","reason":"Explore the gemini topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/gemini.md","json_url":"https://newruntime.com/topics/gemini.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":"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"}]}