Grok 3 Mini
A smaller, more efficient version of Grok 3 from xAI. Represents a new frontier in cost-efficient reasoning, particularly strong on STEM tasks that don't require as much world knowledge. Also features test-time compute and reasoning capabilities through the Grok 3 mini (Think) variant, achieving impressive performance on mathematical and coding benchmarks while being more resource-efficient than the full Grok 3 model.
Specifications
- Parameters
- Unknown
- Architecture
- Decoder-only Transformer
- License
- Proprietary
- Context Window
- 1,000,000 tokens
- Type
- multimodal
- Modalities
- textimagevideo
Benchmark Scores
Graduate-level Problems in Quantitative Analysis (GPQA) evaluates advanced reasoning on graduate-lev...
MMLU-Pro is an enhanced benchmark with over 12,000 challenging questions across 14 domains including...
Long-Context Frontiers benchmark evaluating long-context language models on real-world tasks requiri...
A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI with 11.5...
EgoSchema is a very long-form video question-answering dataset and benchmark for evaluating long vid...
The FACTS Grounding Leaderboard evaluates LLMs' ability to generate factually accurate long-form res...
Advanced Specifications
- Model Family
- Grok
- API Access
- Available
- Chat Interface
- Available
- Variants
- Grok 3 mini (Think)
Capabilities & Limitations
- Capabilities
- reasoningmathematicscodingtest-time-computechain-of-thoughtcost-efficient-reasoningSTEM-tasks
- Notable Use Cases
- cost-efficient reasoningSTEM problem solvingmathematical computationcode generationresource-constrained applications
- Function Calling Support
- Yes
- Tool Use Support
- Yes
