Grok 4.7 is now available in Devin

Cognition1 min read

Grok 4.7 is now live in Devin Desktop and the Devin CLI.

On FrontierCode 1.1, our proprietary benchmark that grades models on real-world engineering tasks based on quality and mergeability, Grok 4.7 is strongest on hard, multi-module backend tasks in Java, Go, and Ruby, where it investigates deeply, reads dependency source, and verifies its work end to end with real integration tests. It scores below Grok 4.6 on the aggregate because it tends to over-scope, producing larger diffs with changes not requested by the evaluation task.

FrontierCode LeaderboardBenchmarks for how well models meet the standards of high-quality production codebasesView Now

FrontierCode 1.1 ExtendedScore

020406080100Score (%)56.2Claude Sonnet 556.3Gemini 3.7 Flash56.5Grok 4.558.2Kimi K359.4Grok 4.760.6GPT-5.6 Sol61.3Grok 4.662.5SWE-263.6Claude Opus 563.6Claude Fable 5.164.5GPT-6 Astra64.9Claude Fable 5

Score is a weighted aggregate of rubric items. Solutions that don’t pass blocking criteria receive 0.

FrontierCode 1.1 ExtendedScorevsCost ($)

$0.00$2.00$4.00$6.00$8.00$10$12$14$16avg cost (USD) per rollout505254565860626466score (%)Fable 5GPT-6 AstraSWE-2Fable 5.1Grok 4.6GPT-5.6 SolGrok 4.7Opus 5Kimi K3

Score: a weighted aggregate of the rubric items. Solutions that don’t pass blocking criteria receive 0.

Cost ($): the mean USD spend per rollout. Each dot is a reasoning effort.

Try Devin Cloud · Download Devin Desktop · Install Devin CLI