Back to all models
G

Grok-2

xAIReleased 2024-08-14
Official Page

xAI's Grok-2 model with real-time knowledge access via X (Twitter) integration, featuring image generation capabilities.

Overall Score
76%
Cost Efficiency
100
Context Window
128K

Strengths

  • ✓Real-time knowledge via X
  • ✓Image generation built-in
  • ✓Good social media integration

Weaknesses

  • ✗Expensive
  • ✗Controversial data sources
  • ✗Less competitive in benchmarks
Architecture
Transformer (MoE)
Parameters
Unknown
Input
$15/M
Output
$15/M

Benchmark Performance

BenchmarkDescriptionScoreCategoryBar
MMLUMassive Multitask Language Understanding86.5%knowledge
HumanEvalCode generation accuracy87.6%coding
MATHMathematical reasoning86.3%math
GSM8KGrade school math89%math
GPQAGraduate-level science Q&A48.1%reasoning
HellaSwagCommon sense reasoning85.3%reasoning
SWE-benchSoftware engineering problems34.7%coding
ARC-CAI2 Reasoning Challenge93%reasoning
AI
ModelBench

The open benchmark platform for comparing the latest AI models and their capabilities.

Platform

  • Compare Models
  • All Models
  • Methodology

AI Labs

  • OpenAI
  • Anthropic
  • Google DeepMind
  • Meta AI

Resources

  • Documentation
  • Benchmark Guide
  • API Reference
Benchmarks are sourced from official model cards and independent evaluations. Data is for informational purposes only.
© 2026 ModelBench. Built for the AI community.