# The most misunderstood graph in AI just got a major update

> Source: <https://aiflash.com/news/155098/>
> Published: 2026-11-20 18:30:05+00:00

**Recommendation:** When evaluating models, test judgment-heavy tasks separately from coding; METR's update shows capability gains on coding do not transfer evenly to tasks requiring judgment.
More in the playbook "Evals and testing for LLM apps": <https://wpnews.pro/playbooks/evals-testing>

A new report from the AI evaluation nonprofit METR finds that some AI capabilities are continuing to improve along an exponential trajectory—but it also indicates that models aren’t quite as good at tasks that require judgment as they are at coding. The report is an update to the organization’s time
