NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Grok Build 0.1
xAI logo

Grok Build 0.1

by xAI · Released May 2026

Multimodal
77.1
avg score
Rank #23
Compare
Better than 93% of all models
Context
256K tokens (~128 books)
Input $/1M
$1.00
Output $/1M
$2.00
Type
multimodal
License
Proprietary
Benchmarks
8 tested
Data as of
About

Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...

Tested on 8 benchmarks · BenchGecko score 77.1. Top scores: LiveBench — Mathematics (78.4%), LiveBench — Reasoning (76.4%), LiveBench — Language (72.5%).

Looking for similar performance at lower cost?
gpt-oss-120b (free) scores 74.2 (96% as good) at $0.00/1M input · 100% cheaper
Capabilities
coding
59.4
#51 globally
reasoning
73.6
#34 globally
math
78.4
#30 globally
knowledge
68.9
#22 globally
language
68.8
#83 globally
Benchmark Scores
Compare All
Tested on 8 benchmarks · Ranked across 5 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

65.4·
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

53.3·
reasoningCompare reasoning →
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

76.4·
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

70.8·
mathCompare math →
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

78.4·
Quick compare:Alibaba logovs Qwen2 7B InstructOpenAI logovs GPT-5.6 TerraOpenAI logovs GPT-5.1-Codex
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
Alibaba logo
Qwen2 7B Instruct
Alibaba
76.5n/a
OpenAI logo
GPT-5.6 Terra
OpenAI
76.5$2.00/1M
OpenAI logo
GPT-5.1-Codex
OpenAI
77.7$1.25/1M
Links
Info
xAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@xAI
BenchGecko API
grok-build-0-1
Specifications
  • Typemultimodal
  • Context256K tokens (~128 books)
  • ReleasedMay 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.004
Available On
xAI logoxAI$1.00
Categories
codingreasoningmathknowledgelanguage
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
Alibaba logoQwen2 7B Instruct
76.5
OpenAI logoGPT-5.6 Terra
76.5
OpenAI logoGPT-5.1-Codex
77.7
Microsoft logophi-3-small 7.4B
79.2
Grok Build 0.1 is a proprietary multimodal AI model by xAI, released in May 2026. It has an average benchmark score of 77.1. Context window: 256K tokens.

Related Models

Qwen2 7B Instruct · AlibabaGPT-5.6 Terra · OpenAIGPT-5.1-Codex · OpenAIphi-3-small 7.4B · Microsoftgpt-oss-120b (free) · OpenAI

Benchmarks

LiveBench — MathematicsLiveBench — ReasoningLiveBench — LanguageLiveBench — Data AnalysisLiveBench — Overall

Related Pages

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

Key facts · as of 2026-10-05

  • Grok Build 0.1 by xAI. BenchGecko score 77.1, rank 23 of 312 scored models (normalized average of public benchmark scores).
  • List price $1.00 input · $2.00 output per 1M tokens (as of 2026-10-05).
  • Gecko Tests: Who Are You B (Knows who made it) · Tokenizer Tax B (44% more tokens outside English).

How to cite · data as of 2026-10-05

Grok Build 0.1 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/grok-build-0-1

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