SOC 27-3023 · News Analysts, Reporters, and Journalists
Journalism, tested on the work
File a story with an AI assistant, from sources whose claims only settle when someone checks them.
The assignment
What the candidate is asked to do
A short piece ready for an editor, written from a packet of releases, documents and transcripts, with an AI assistant available throughout.
Time: 40 to 60 minutes, hard-capped 15 to 20 minutes past whatever the case states and never above 75, with a short written debrief after. Paused time does not count against either.
SOC 27-3023
News Analysts, Reporters, and Journalists. The benchmark is derived from live postings mapped to that code and re-derived each quarter.
What the reviewer watches for
The journalism failure modes
Each maps to a scored dimension, so the reviewer's finding arrives with the moment attached.
Is the story named — what it claims, and what would make it wrong — before any copy exists?
Whether the opening move asks what is true, what is wrong, or what the options are — and whether a constraint or criterion is named in the same breath.
Is the number in the release traced to the document behind it, and the document opened?
Whether sources are demanded for a specific claim rather than requested in general — and whether at least one is actually opened.
Is the publish call kept, or is the piece the assistant's draft with a byline?
Whether the split between the assistant's work and the candidate's own acts is deliberate rather than convenient, read from the record of both.
Why this bank
Why we built the journalism bank
Journalism is the occupation whose stated professional ethic is the construct itself — verify before publishing — which makes it the sharpest public demonstration of what the instrument reads, and the one bank a reviewing reporter can sit themselves.
This bank is live and has passed author review at launch quality.
https://olive.is/benchmarks · Edition 2026 Q3Named up front
File a story with an AI assistant, from sources whose claims only settle when someone checks them.
The construct
Six dimensions, scored separately
- D1 · Problem framing Did the first move go after understanding, or straight for output?
- D2 · Evidence sourcing Did they demand evidence for the claim that mattered?
- D3 · Delegation boundary What did they keep, and what did they hand over?
- D4 · Working structure Did anything exist between the brief and the answer?
- D5 · Output rejection Was anything the assistant produced refused, and on what grounds?
- D6 · Verification Was anything tested against the world, and did the result change something?
SOC 27-3023
Run one journalism role, free
Ten attempts a month against this bank, with the full six-dimension report on every one. No card, no salesperson.