AINewsnow

The Dayjob Tax Benchmark: AI Agents Pass Under 11%

Originally published at webofmike.com on 2026-11-03. The demo repo and every command in it were run before publishing. Surge AI's Dayjob: Tax benchmark landed on Hacker News on 2026-10-28 and sat at the top of the page for a day ( 247 points, 154 comments ). The number that stuck: Claude Sonnet 5.5…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-04 20:47 · DEV Community — AI
    The Dayjob Tax Benchmark: AI Agents Pass Under 11%

More stories

  1. Anthropic reports 1,100% revenue surge and $895B compute commitments ahead of IPO — Reuters AI
  2. Anthropic says Claude helped map first 3D structure of bacterial vault particle — Anthropic (X)
  3. Elon Musk Says Grok Bot Costs Were ‘Unsustainably High’ Amid Complaints Over Usage Limits — Forbes AI
  4. Cat Wu, product lead for Claude Code, leaves Anthropic — Business Insider AI
  5. Developers document lessons from running multiple Claude Code sessions in parallel — DEV Community — AI
  6. Anthropic launches Message Threads beta, cutting agent request sizes from 800 KB to 1.8 KB — Anthropic (X)
  7. Anthropic confirms new Claude Code limits to block recreation of existing video games — Techmeme
  8. Anthropic discloses nearly $900 billion in planned spending ahead of IPO — Axios AI+

Get the daily brief of stories like this at 6:30 every morning →