DAYJOB: Tax

Search everything

Mentions · 7d1
Mentions · 30d1
All mentions1
First seenOct 28, 2026
Last mentioned2d ago

Timeline

1 articles · newest first

Surge AI benchmarks agents on 50 professional tax assignments

Claude Sonnet 5.5 leads DAYJOB: Tax at a 10.8% pass rate under a 95% rubric threshold.

Hacker News · AIOct 28, 15:46 UTC · 2d agoAI research HN 44 points · 29 comments3

Appears with

Claude Fable 5.1ai model · 1
Claude Sonnet 5.5ai model · 1
Surge AIorganization · 1
Claude Opus 5.5ai model · 1
Astraai model · 1

Entities are extracted by the model from each article. First seen Oct 28, 2026, last mentioned 2d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.