NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Grok-2 (Dec 2024)
xAI logo

Grok-2 (Dec 2024)

by xAI · Released Jan 2024

28.9
avg score
Rank #253
Compare
Better than 19% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text
License
Proprietary
Benchmarks
9 tested
Data as of
About

Tested on 9 benchmarks · BenchGecko score 28.9. Top scores: Lech Mazur Writing (63.6%), MATH level 5 (63.5%), Aider — Code Editing (58.6%).

Capabilities
coding
40.4
#134 globally
reasoning
7.2
#193 globally
math
25.4
#210 globally
knowledge
51.0
#120 globally
general
42.0
#61 globally
Benchmark Scores
Compare All
Tested on 9 benchmarks · Ranked across 5 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
Aider — Code Editing

Code editing benchmark from the Aider project. Measures ability to apply targeted code changes while maintaining correctness and style.

58.6·
WeirdML

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

22.2·
reasoningCompare reasoning →
SimpleBench

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

7.2·
mathCompare math →
MATH level 5

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

63.5·
OTIS Mock AIME 2024-2025

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

11.4·
FrontierMath-2025-02-28-Private

Original research-level math problems created by professional mathematicians. Problems are unpublished and cannot be memorized.

1.2·
Quick compare:Meta logovs Llama 3.3 70B Instruct (free)Mistral AI logovs Devstral 2 2512Mistral AI logovs Mistral 7B Instruct V0.2
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
Meta logo
Llama 3.3 70B Instruct (free)
Meta
28.9Free
Mistral AI logo
Devstral 2 2512
Mistral AI
28.8$0.40/1M
Mistral AI logo
Mistral 7B Instruct V0.2
Mistral AI
29.3n/a
Links
Info
xAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@xAI
BenchGecko API
grok-2-dec-2024
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseProprietary
  • Statusbenchmark-only
Available On
xAI logoxAIn/a
Categories
codingreasoningmathknowledgegeneral
Learn More
transformertokens
Share & Export
Tweet
Related Models
Meta logoLlama 3.3 70B Instruct (free)
28.9
Mistral AI logoDevstral 2 2512
28.8
Mistral AI logoMistral 7B Instruct V0.2
29.3
tencent logoHunyuan A13B Instruct
29.3
Grok-2 (Dec 2024) is a proprietary text AI model by xAI, released in January 2024. It has an average benchmark score of 28.9.

Related Models

Llama 3.3 70B Instruct (free) · MetaDevstral 2 2512 · Mistral AIMistral 7B Instruct V0.2 · Mistral AIHunyuan A13B Instruct · tencentGPT-5.4 Nano · OpenAI

Benchmarks

Lech Mazur WritingMATH level 5Aider — Code EditingDtbenchGPQA diamond

Related Pages

xAI · ProviderxAI · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • Grok-2 (Dec 2024) by xAI. BenchGecko score 28.9, rank 253 of 312 scored models (normalized average of public benchmark scores).
  • List price n/a input · n/a output per 1M tokens (as of 2026-04-09).

How to cite · data as of 2026-04-09

Grok-2 (Dec 2024) · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/grok-2-dec-2024

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