Inference
EN
xAI

Grok 3 Mini

Grok 3 Mini is a reasoning model from xAI. 8 benchmarks count toward its index, in 4 categories.

  • Closed weights
  • Reasoning
  • Input: text
  • Released 2025-02
RankedEnough results for an index.
IndexAll categories, out of 100.44.3±9.7Median 51.0
CoverageIndex weight that has results.60%
SpeedOutput tokens per second.65/sMedian 67/s
First tokenSeconds to the first output token.32.4 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.30Median $0.60
Output / 1MUS dollars per 1M output tokens.$0.50Median $2.55
ContextMaximum tokens in one request.128KMedian 262K
EloLMArena rating and rank.1370±5 #190Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.1 counted51.4—
ReasoningLogic problems and puzzles.2 counted37.0179 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.1 counted48.7—
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.4 counted43.9110 / 168

Results

8 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for CodeCoding74.8%2 / 12
MATH level 5Math88.1% ±0.918 / 88
American Invitational Mathematics Examination 2024Math89.5%8 / 27
OTIS Mock AIME 2024-2025Math77.8% ±6.390 / 200
Graduate-Level Google-Proof Q&AKnowledge80.3%65 / 141
GPQA diamond · Epoch AIKnowledge75.5% ±2.8106 / 217
FrontierMath-2025-02-28-PrivateMath5.9% ±1.443 / 69
ARC-AGI-1 (semi-private)Reasoning16.5%108 / 126
ARC-AGI-2 (semi-private)Reasoning0.4%117 / 131
FrontierMath-Tier-4-2025-07-01-PublicMath0.0%3 / 36
FrontierMath-2025-02-28-PublicMath0.0%33 / 64
ARC-AGI-2 (public eval)Reasoning0.0%102 / 122
ARC-AGI-1 (public eval)Reasoning17.6%103 / 116

Sources

BenchLMCC BY-NC 4.0Epoch AICC BYARC Prize FoundationTerms restrict reuse

History

5 releases
Index45.3 → 44.3
23 Oct 202612 Nov 2026
Output / 1M$0.50 → $0.50
23 Oct 202612 Nov 2026

Questions

How much does Grok 3 Mini cost?
$0.30 per 1M input tokens, $0.50 per 1M output tokens.
How good is Grok 3 Mini?
Its index is 44.3 out of 100. That is place 183 of 283 ranked models.
What is Grok 3 Mini best at?
Math: 43.9 out of 100, place 110 of 168.
How fast is Grok 3 Mini?
65 output tokens per second, 32.4 s to the first token.
What is the context window of Grok 3 Mini?
128K tokens.
Is Grok 3 Mini open source?
No. Its weights are not published.
When was Grok 3 Mini released?
February 2025.

Badge

Grok 3 Mini on Inference360: place 183 of 283, index 44.3
HTML
<a href="https://inference360.ai/models/grok-3-mini"><img src="https://inference360.ai/badges/grok-3-mini.svg" alt="Grok 3 Mini on Inference360: place 183 of 283, index 44.3" height="20"></a>
Markdown
[![Grok 3 Mini on Inference360: place 183 of 283, index 44.3](https://inference360.ai/badges/grok-3-mini.svg)](https://inference360.ai/models/grok-3-mini)

Compare with

DeepSeek V3.244.2Gemma 4 26B A4B44.5o144.5Grok 3 [Beta]39.3Grok 229.1

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from xAI

All models
Grok 3 [Beta]39.3Grok 450.0Grok Code Fast 141.2Grok 229.1Grok 2 miniUnranked