Inference
EN
xAI

Grok 2 mini

Grok 2 mini is a standard model from xAI in the Grok 2 family. It has 5 scored results in 3 categories. It has no index.

  • Closed weights
  • Standard
  • Input: text
  • Released 2024-08
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.45%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.—Median 262K
EloLMArena rating and rank.1281±4 #277Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.1 counted26.4—
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.1 counted30.4—
KnowledgeFacts and expert knowledge.3 counted31.2—
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.None counted——

Results

5 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Massive Multitask Language UnderstandingKnowledge86.2%14 / 34
Evaluating Large Language Models Trained on CodeCoding85.7%13 / 22
Massive Multitask Language Understanding ProfessionalKnowledge72.0%54 / 75
Massive Multi-discipline Multimodal UnderstandingMultimodal63.2%23 / 28
Graduate-Level Google-Proof Q&AKnowledge51.0%121 / 141

Sources

BenchLMCC BY-NC 4.0

Questions

Is Grok 2 mini open source?
No. Its weights are not published.
When was Grok 2 mini released?
August 2024.

More from xAI

All models
Grok 229.1Grok 3 Mini44.3Grok 3 [Beta]39.3Grok 450.0Grok Code Fast 141.2