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

Grok 3

by xAI · Released Jan 2024

44.6
avg score
Rank #175
Compare
Better than 44% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text
License
Proprietary
Benchmarks
19 tested
Data as of
About

Tested on 19 benchmarks · BenchGecko score 44.6. Top scores: MATH level 5 (88.8%), HELM — IFEval (88.4%), HELM — WildBench (84.9%).

Capabilities
coding
45.3
#114 globally
reasoning
28.4
#126 globally
math
38.9
#158 globally
knowledge
62.6
#44 globally
agentic
2.1
#71 globally
language
88.4
#21 globally
Benchmark Scores
Compare All
Tested on 19 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.

53.3·
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

37.2·
reasoningCompare reasoning →
HELM — WildBench

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

84.9·
SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

23.3·
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

5.5·
mathCompare math →
MATH level 5

Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.

88.8·
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

55.5·
HELM — Omni-MATH

Stanford HELM evaluation of mathematical reasoning across diverse problem types.

46.4·
Quick compare:Alibaba Qwen logovs Qwen3.7 FlashAnthropic logovs Claude Sonnet 4.5Anthropic logovs Claude Sonnet 4
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
Alibaba Qwen logo
Qwen3.7 Flash
Alibaba Qwen
44.6$0.03/1M
Anthropic logo
Claude Sonnet 4.5
Anthropic
44.6$3.00/1M
Anthropic logo
Claude Sonnet 4
Anthropic
44.5$3.00/1M
Links
Info
xAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@xAI
BenchGecko API
grok-3
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseProprietary
  • Statusbenchmark-only
Available On
xAI logoxAIn/a
Categories
codingreasoningmathknowledgeagenticlanguage
Learn More
transformertokens
Share & Export
Tweet
Related Models
Alibaba Qwen logoQwen3.7 Flash
44.6
Anthropic logoClaude Sonnet 4.5
44.6
Anthropic logoClaude Sonnet 4
44.5
Google DeepMind logoGemini 2.0 Flash
44.4
Grok 3 is a proprietary text AI model by xAI, released in January 2024. It has an average benchmark score of 44.6.

Related Models

Qwen3.7 Flash · Alibaba QwenClaude Sonnet 4.5 · AnthropicClaude Sonnet 4 · AnthropicGemini 2.0 Flash · Google DeepMindQwen3 235B A22B Instruct 2507 · Alibaba Qwen

Benchmarks

MATH level 5HELM — IFEvalHELM — WildBenchHELM — MMLU-ProLech Mazur Writing

Related Pages

xAI · ProviderxAI · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-05-03

  • Grok 3 by xAI. BenchGecko score 44.6, rank 175 of 312 scored models (normalized average of public benchmark scores).
  • List price n/a input · n/a output per 1M tokens (as of 2026-05-03).

How to cite · data as of 2026-05-03

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

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