Grok 4.6
Grok 4.6 is a released general-purpose model optimized for sustained agentic knowledge work, coding, application creation, and other long-running tasks across several hosted platforms.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 84.8
Primary benchmark evidence shows broad gains over Grok 4.5 in coding and agentic work, while API and multi-platform access create high deployment exposure. The release claims expanded predeployment and postdeployment safeguards but provides no detailed system card, and it does not establish whether model artifacts are open or proprietary.
News tied to Grok 4.6
The model score of 84.8 rates this model's risk profile. The overall Doom Index of 59.6 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
SpaceXAI releases Grok 4.6 for long-running agent work
SpaceXAI released Grok 4.6 through its API and multiple agent platforms, reporting gains over Grok 4.5 on coding, knowledge-work, and long-horizon agent evaluations, plus self-testing and verification during extended tasks.
- Full item contribution
- +0.25
- Grok 4.6 equal share
- +0.25
Model score history
- R1Doom Score 84.8
Initial profile from the dated Grok 4.6 release, benchmark results, deployment channels, and safeguard disclosure.
12 Aug 2026