Grok 3 mini
READER SUMMARYA cost-efficient Grok 3 beta reasoning tier optimized for mathematics, coding and other STEM tasks through reinforcement-learned test-time compute.
Why this model scores 71.2
The mini tier trails flagship world knowledge but demonstrates strong reasoning and coding with cost-efficient inference. Test-time reasoning raises autonomy, while early hosted rollout constrains deployment and control difficulty compared with open or fully general-availability systems.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
News tied to Grok 3 mini
The model score of 71.2 rates this model's risk profile. The overall Doom Index of 63.2 measures the recalibrated complete evidence corpus. These values answer different questions.
Each article's leave-one-out 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 are recalculated from their technical profile and related news, but never feed back into the overall index.
SpaceXAI unveils Grok 3 and Grok 3 mini reasoning models
SpaceXAI unveiled Grok 3 and Grok 3 mini, beta reasoning models trained with large-scale reinforcement learning and ten times the compute of its prior generation, with user rollout beginning.
- Full item contribution
- +0.04
- Grok 3 mini equal share
- +0.02
Model score history
- R1Doom Score 71.2
Initial exact profile for the separately named February 2025 Grok 3 mini beta tier.
12 Aug 2026