# Cognition launches FrontierCode 2.0, a coding benchmark where top model scores 45%

> Original title: Introducing FrontierCode 2.0: our new coding benchmark that measures a model’s ability to go beyond the spec.

- Source: Cognition
- Published: 2026-10-27T17:24:17.000Z
- Bad Influence: https://badinfluence.news/items/shho3qw55s1g1puqsmrl9f6ri
- Original: https://x.com/cognition/status/2115132488775524793

## Summary

Cognition introduces FrontierCode 2.0, a coding benchmark that tests whether a model's pull request should be merged, not just whether it meets a spec. The benchmark uses more diverse tasks, larger scopes, higher mergeability standards, and deliberately underspecified prompts that require model judgment. The top model scores 45%, which Cognition says shows the benchmark is far from saturated.

## Post

Introducing FrontierCode 2.0: our new coding benchmark that measures a model’s ability to go beyond the spec.

Most coding evals measure a model’s ability to write code that meets a spec. With FrontierCode 1.0, we asked a new question: would you actually merge the PR?

FrontierCode 2.0 is comprised of more diverse tasks, featuring larger scopes and higher mergeability standards. We are now asking: not only would you merge this PR, but should you?

One key feature of FrontierCode 2.0 is underspecified prompts. Rather than including every engineering decision, prompts are deliberately ambiguous, giving the models room to demonstrate their judgment.

The result is a benchmark that is far from saturated, with the top model scoring just 45%.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVplDzybQAAEbbZ.jpg&mode=thumb&exp=1793404800&sig=4254b68047e045fa)