Model
Model explorer

Grok-2 mini

CLOSED
SpaceXAI · Grok 2 family · released Aug 13, 2024

Smaller, faster, cost-efficient sibling of Grok-2 launched in the same beta; no distinct API price could be confirmed post-2024.

ReasoningCodingVisionFunction callingTool useAgentic
1129.5
Elo · rank #184
Parameters
Undisclosed
Active params
Undisclosed
Context
131K tokens
Architecture
Mixture-of-Experts (size undisclosed by xAI; smaller sibling of Grok-2)
License
Proprietary
Languages
—
API price (in/out)
No hosted API
Modalities
text · vision
Benchmark results
Bar shows position within the tracked field; marker = field best
DocVQAVision93.2%#19
best: Qwen2-VL-72B · 96.5%
GPQA DiamondReasoning51.0%#183
best: GPT-5.6 · 94.6%
HumanEvalCoding85.7%#39
best: Claude Opus 4.5 · 99.4%
MATH-500Math73.0%#85
best: GPT-5 · 99.4%
MathVistaVision68.1%#32
best: Seed 2.1 Pro · 90.7%
MMLU-ProKnowledge72.0%#87
best: Claude Fable 5 · 91.5%
MMLUKnowledge86.2%#44
best: OpenAI o3 · 92.9%
MMMUVision63.2%#70
best: Claude Fable 5 · 89.3%
Run it locally
Closed weights — available via API only. No local deployment.
Input / M tok
—
Output / M tok
—
Grok 2 family
Elo progression across releases
Grok-2Aug 20241228.2Grok-2 miniAug 20241129.5
Resources
DOCSdocs.x.aiAPIAvailable via SpaceXAI API
API price — · each benchmark row carries its own source badge (see methodology)