A Coding Benchmark That Tests Judgment, Not Spec-Following, Stumps Every Model at 45%

FrontierCode 2.0 asks whether a model can go beyond the specification — and the best performer managed just 45%.

A new coding benchmark is measuring the thing most evaluations ignore: judgment. According to @ISanjayD, FrontierCode 2.0 — released under the COGNITION banner — tests whether a model can go beyond the literal spec, and the top model scored just 45%. That number is the story. On many conventional coding benchmarks, frontier models now cluster near the ceiling. A benchmark where the best result is a failing grade is either poorly calibrated or measuring something genuinely hard.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Proin pharetra nonummy pede. Mauris et orci. Aenean nec lorem. In porttitor. Donec laoreet nonummy augue. Suspendisse dui purus, scelerisque at, vulputate vitae, pretium mattis, nunc. Mauris eget neque at sem venenatis eleifend. Ut nonummy. Fusce aliquet pede non pede. Suspendisse dapibus lorem pellentesque magna integer malesuada.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief