Urgent.News

What's breaking now, across thousands of outlets.

AI

Your AI coding agent could cost 5x more depending on the harness, benchmark finds

The same AI model can cost up to five times more to run depending on the coding agent harness it’s The post Your AI coding agent could cost 5x more depending on the harness, benchmark finds appeared first on The New Stack .

Your AI coding agent could cost 5x more depending on the harness, benchmark finds

A new benchmark conducted by The New Stack has found that the cost of running an AI model for coding agents can vary significantly depending on the harness used. The benchmark tested 22 configurations across five open-weight models, consuming approximately 83 billion tokens. The model itself accounted for 92.8% of the cost differences, but the harness still had a considerable impact.

Nearly 65% of the estimated inference spending went to runs that failed verification or timed out. The rankings of different harness configurations shifted significantly when the AI model changed, with a median of 11 ranking positions changing across models. Failed runs accounted for 52.7% of estimated inference spending, with timeouts adding another 11.8%.

Brief written by urgent.news from The New Stack's own syndicated text. Machine-written — may contain errors; check the original before relying on it.

Read the original at thenewstack.io →

More in AI

AI Daily Digest November 18, 2026: Microsoft Builds the Agent Cloud, OpenAI Agents Enter the Hospital, Robotics Money Floods In

AI Daily Digest · November 18, 2026 · curated by KD Agentic 1. Microsoft Ignite 2026: the operating layer for enterprise agents goes GA Microsoft opened Ignite 2026 in Seattle with a message that has…

  • Microsoft unveils Agent Cloud on Azure, enabling resource management via agent requests
  • Azure Copilot's deployment agent goes GA, translating natural language into infrastructure
  • Azure IQ platform consolidates enterprise context management for agent efficiency

From Chat to Deliverables: How to Design Reliable AI Workflows

The Limitation of Pure Conversational AI In modern knowledge work, relying solely on conversational prompts—such as "draft an industry analysis report" or "prepare a project plan"—frequently falls…

  • Conversational AI struggles with formal deliverables due to Context Decay and Drift.
  • WorkBuddy AI workspace automates task planning and integrates tools for reliable AI workflows.

More from Tuesday 17 November →