# Gemini 4 Carbon scores 40% on FrontierCode 2.0, near state of the art

> Original title: We've evaluated Gemini 4 Carbon and Gemini 4 Argon on FrontierCode 2.0, our coding benchmark that measure's a model's ability to go beyon...

- Source: Cognition
- Published: 2026-10-30T01:45:06.000Z
- Bad Influence: https://badinfluence.news/items/iwj15rypn7hz0j32t6f15tdzj
- Original: https://x.com/cognition/status/2115983299432820864

## Summary

Cognition says Gemini 4 Carbon scores 40% on its FrontierCode 2.0 coding benchmark at $4.04 per task, placing it behind Claude Opus 5.5, GPT-6 Astra, and Claude Sonnet 5.5. Gemini 4 Argon scores 26.3% at $6.41 per task, ahead of Muse Wonder 1.0 but behind Claude Haiku 5.5 and Grok 4.7. Full scores are on the FrontierCode leaderboard at cognition.com/frontiercode.

## Post

We've evaluated Gemini 4 Carbon and Gemini 4 Argon on FrontierCode 2.0, our coding benchmark that measure's a model's ability to go beyond the spec.

Gemini 4 Carbon scores near SOTA with a score of 40% and a cost of $4.04 per task, behind Claude Opus 5.5, GPT-6 Astra, and Claude Sonnet 5.5.

Gemini 4 Argon scores 26.3% with a cost of $6.41 per task, ahead of Muse Wonder 1.0, but behind Claude Haiku 5.5 and Grok 4.7.

See the leaderboard with full scores: https://cognition.com/frontiercode

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHV16aeMbsAAffLi.jpg&mode=thumb&exp=1793577600&sig=3dc8c133a77aa782)