NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Grok 3 Mini Beta
xAI logo

Grok 3 Mini Beta

by xAI · Released Apr 2025

Preview
53.1
avg score
Rank #129
Compare
Better than 59% of all models
Context
131K tokens (~66 books)
Input $/1M
$0.30
Output $/1M
$0.50
Type
text
License
Proprietary
Benchmarks
7 tested
Data as of
About

Grok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-heavy tasks that don’t demand...

Tested on 7 benchmarks · BenchGecko score 53.1. Top scores: Chatbot Arena Elo — Overall (1357.4%), HELM — IFEval (95.1%), HELM — MMLU-Pro (79.9%).

Looking for similar performance at lower cost?
Gemma 4 31B scores 53.3 (100% as good) at $0.09/1M input · 70% cheaper
Capabilities
coding
49.3
#95 globally
reasoning
65.1
#49 globally
math
31.8
#180 globally
knowledge
73.7
#10 globally
language
95.1
#1 globally
Benchmark Scores
Compare All
Tested on 7 benchmarks · Ranked across 6 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
Aider polyglot

Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.

49.3·
reasoningCompare reasoning →
HELM — WildBench

Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.

65.1·
mathCompare math →
HELM — Omni-MATH

Stanford HELM evaluation of mathematical reasoning across diverse problem types.

31.8·
Quick compare:DeepSeek logovs DeepSeek R1 Distill Llama 8BxAI logovs Grok 4 FastGoogle DeepMind logovs Gemma 4 31B
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · xAI Grok 3
Jan 2024
44.6
n/an/actx19 benchmarks
Apr 2025
67.9+23.3
$3.00/M in131Kctx6 benchmarks
Apr 2025
53.1-14.8
$0.30/M in(-2.70)131Kctx7 benchmarks
See the full Grok 3 family →
Similar Models
DeepSeek logo
DeepSeek R1 Distill Llama 8B
DeepSeek
53.1n/a
xAI logo
Grok 4 Fast
xAI
53.1n/a
Google DeepMind logo
Gemma 4 31B
Google DeepMind
53.3$0.09/1M
Links
Info
xAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@xAI
BenchGecko API
grok-3-mini-beta
Specifications
  • Typetext
  • Context131K tokens (~66 books)
  • ReleasedApr 2025
  • LicenseProprietary
  • Statuspreview
  • Cost / Message~$0.001
Available On
xAI logoxAI$0.30
Categories
codingreasoningmathknowledgelanguage
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
DeepSeek logoDeepSeek R1 Distill Llama 8B
53.1
xAI logoGrok 4 Fast
53.1
Google DeepMind logoGemma 4 31B
53.3
meituan logoLongCat Flash Chat
53.4
Grok 3 Mini Beta is a proprietary text AI model by xAI, released in April 2025. It has an average benchmark score of 53.1. Context window: 131K tokens.

Related Models

DeepSeek R1 Distill Llama 8B · DeepSeekGrok 4 Fast · xAIGemma 4 31B · Google DeepMindLongCat Flash Chat · meituanQwen3.5-35B-A3B · Alibaba Qwen

Benchmarks

Chatbot Arena Elo — OverallHELM — IFEvalHELM — MMLU-ProHELM — GPQAHELM — WildBench

Related Pages

xAI · ProviderxAI · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-05-03

  • Grok 3 Mini Beta by xAI. BenchGecko score 53.1, rank 128 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.30 input · $0.50 output per 1M tokens (as of 2026-05-03).

How to cite · data as of 2026-05-03

Grok 3 Mini Beta · benchmarks, pricing and providers. BenchGecko, data as of 2026-05-03. https://benchgecko.ai/model/grok-3-mini-beta

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP