PulseAugur
EN
LIVE 09:03:15

New DAYJOB benchmark reveals AI struggles with long-horizon professional tasks

By PulseAugur Editorial · [1 sources] ·

A new benchmark called DAYJOB has been developed to evaluate AI agents on long-horizon professional tasks, particularly in healthcare and finance. The benchmark consists of 130 tasks, each requiring an average of 13.6 to 16.6 hours for a human professional to complete. Even advanced models like Claude Opus 5.5 struggle, passing only around 24% of healthcare and finance tasks, indicating significant challenges for AI in complex, multi-step professional work. The researchers found that agents often accept flawed premises and propagate errors throughout their analyses. AI

IMPACT Highlights significant limitations in current AI capabilities for complex, multi-step professional tasks, indicating a need for improved reasoning and error-handling.

RANK_REASON The cluster describes a new benchmark for AI evaluation, presented in an arXiv paper. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New DAYJOB benchmark reveals AI struggles with long-horizon professional tasks

How we ranked this

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a new benchmark for AI evaluation, presented in an arXiv paper. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Stephanie Finley, Liudas Panavas, Thomas Mikkelson, Cam Hinton, Stacey Ganss, Bradley Monton, Emily Kendall, Michelle Spradlin, Lydia Bye, Michael O'Brien, Lauren Ylvisaker, Derek Ray, Suhaas Garre, Sushant Mehta, Edwin Chen ·

    DAYJOB: A Benchmark for Long-Horizon Professional Work

    arXiv:2610.01306v1 Announce Type: new Abstract: Professional work often starts with a brief request that leaves the professional to work out what is needed, which documents matter, and whether the request's premise holds. We introduce DAYJOB, a benchmark of 130 tasks built by pro…

RELATED ENTITIES

RELATED TOPICS